_
RobertoLofaro.com - Knowledge Portal - human-generated content
Change, with and without technology
for updates on publications, follow @robertolofaro on Instagram or @changerulebook on Twitter, you can also support on Patreon or subscribe on YouTube


_

You are now here: AI Ethics Primer - search within the bibliography - version 0.4 of 2023-12-13 > (tag cloud) >tag_selected: interpretability


Currently searching for:

if you need more than one keyword, modify and separate by underscore _
the list of search keywords can be up to 50 characters long


if you modify the keywords, press enter within the field to confirm the new search key

Tag: interpretability

Bibliography items where occurs: 196
The AI Index 2022 Annual Report / 2205.03468 / ISBN:https://doi.org/10.48550/arXiv.2205.03468 / Published by ArXiv / on (web) Publishing site
Chapter 3 Technical AI Ethics
Appendix


Ethics of AI: A Systematic Literature Review of Principles and Challenges / 2109.07906 / ISBN:https://doi.org/10.48550/arXiv.2109.07906 / Published by ArXiv / on (web) Publishing site
5 Detail results and analysis


The Different Faces of AI Ethics Across the World: A Principle-Implementation Gap Analysis / 2206.03225 / ISBN:https://doi.org/10.48550/arXiv.2206.03225 / Published by ArXiv / on (web) Publishing site
3 Study Methodology
5 Evaluation of Ethical Principle Implementations
6 Gap Mitigation


A Framework for Ethical AI at the United Nations / 2104.12547 / ISBN:https://doi.org/10.48550/arXiv.2104.12547 / Published by ArXiv / on (web) Publishing site
1. Problems with AI


Worldwide AI Ethics: a review of 200 guidelines and recommendations for AI governance / 2206.11922 / ISBN:https://doi.org/10.48550/arXiv.2206.11922 / Published by ArXiv / on (web) Publishing site
5 Discussion


On the Current and Emerging Challenges of Developing Fair and Ethical AI Solutions in Financial Services / 2111.01306 / ISBN:https://doi.org/10.48550/arXiv.2111.01306 / Published by ArXiv / on (web) Publishing site
3 Practical Challengesof Ethical AI


Implementing Responsible AI: Tensions and Trade-Offs Between Ethics Aspects / 2304.08275 / ISBN:https://doi.org/10.48550/arXiv.2304.08275 / Published by ArXiv / on (web) Publishing site
II. Underlying Aspects


QB4AIRA: A Question Bank for AI Risk Assessment / 2305.09300 / ISBN:https://doi.org/10.48550/arXiv.2305.09300 / Published by ArXiv / on (web) Publishing site
2 The Question Bank: QB4AIRA


Normative Ethics Principles for Responsible AI Systems: Taxonomy and Future Directions / 2208.12616 / ISBN:https://doi.org/10.48550/arXiv.2208.12616 / Published by ArXiv / on (web) Publishing site
3 Taxonomy of ethical principles


Artificial Intelligence across Europe: A Study on Awareness, Attitude and Trust / 2308.09979 / ISBN:https://doi.org/10.48550/arXiv.2308.09979 / Published by ArXiv / on (web) Publishing site
2 Results


Exploring the Power of Creative AI Tools and Game-Based Methodologies for Interactive Web-Based Programming / 2308.11649 / ISBN:https://doi.org/10.48550/arXiv.2308.11649 / Published by ArXiv / on (web) Publishing site
11 Bias Awareness: Navigating AI-Generated Content in Education


Building Trust in Conversational AI: A Comprehensive Review and Solution Architecture for Explainable, Privacy-Aware Systems using LLMs and Knowledge Graph / 2308.13534 / ISBN:https://doi.org/10.48550/arXiv.2308.13534 / Published by ArXiv / on (web) Publishing site
V. Market analysis of LLMs and cross-industry use cases


The Promise and Peril of Artificial Intelligence -- Violet Teaming Offers a Balanced Path Forward / 2308.14253 / ISBN:https://doi.org/10.48550/arXiv.2308.14253 / Published by ArXiv / on (web) Publishing site
3 Emerging dual-use risks and vulnerabilities in AI systems
5 Research directions in AI safety and violet teaming


The AI Revolution: Opportunities and Challenges for the Finance Sector / 2308.16538 / ISBN:https://doi.org/10.48550/arXiv.2308.16538 / Published by ArXiv / on (web) Publishing site
Executive summary
1 Introduction
5 Challenges


Ethical Framework for Harnessing the Power of AI in Healthcare and Beyond / 2309.00064 / ISBN:https://doi.org/10.48550/arXiv.2309.00064 / Published by ArXiv / on (web) Publishing site
1 Introduction
2 Black box and lack of transparency
3 Bias and fairness


FUTURE-AI: Guiding Principles and Consensus Recommendations for Trustworthy Artificial Intelligence in Medical Imaging / 2109.09658 / ISBN:https://doi.org/10.48550/arXiv.2109.09658 / Published by ArXiv / on (web) Publishing site
4. Traceability - For Transparent and Dynamic AI in Medical Imaging
5. Usability - For Effective and Beneficial AI in Medical Imaging
7. Explainability - For Enhanced Understanding of AI in Medical Imaging
9. Discussion and Conclusion


A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics / 2310.05694 / ISBN:https://doi.org/10.48550/arXiv.2310.05694 / Published by ArXiv / on (web) Publishing site
4. Usage and data for healthcare LLM
5. Improving fairness, accountability, transparency, and ethics


Ethics of Artificial Intelligence and Robotics in the Architecture, Engineering, and Construction Industry / 2310.05414 / ISBN:https://doi.org/10.48550/arXiv.2310.05414 / Published by ArXiv / on (web) Publishing site
3. Ethics of AI and Robotics
5. Ethical Issues of AI and Robotics in AEC Industry


Towards A Unified Utilitarian Ethics Framework for Healthcare Artificial Intelligence / 2309.14617 / ISBN:https://doi.org/10.48550/arXiv.2309.14617 / Published by ArXiv / on (web) Publishing site
Abstract
Method
Results and Discussion
A Unified Utilitarian Ethics Framework
Theory and Practical Implications
Conclusion


A Conceptual Algorithm for Applying Ethical Principles of AI to Medical Practice / 2304.11530 / ISBN:https://doi.org/10.48550/arXiv.2304.11530 / Published by ArXiv / on (web) Publishing site
Abstract
1 Introduction
2 Ethical concerns of AI in medicine
3 Ethical datasets and algorithm development guidelines
4 Towards solving key ethical challenges in Medical AI


Responsible AI Pattern Catalogue: A Collection of Best Practices for AI Governance and Engineering / 2209.04963 / ISBN:https://doi.org/10.48550/arXiv.2209.04963 / Published by ArXiv / on (web) Publishing site
2 Methodology
5 Product Patterns


FUTURE-AI: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare / 2309.12325 / ISBN:https://doi.org/10.48550/arXiv.2309.12325 / Published by ArXiv / on (web) Publishing site
METHODS


Unpacking the Ethical Value Alignment in Big Models / 2310.17551 / ISBN:https://doi.org/10.48550/arXiv.2310.17551 / Published by ArXiv / on (web) Publishing site
1 Introduction
3 Investigating the Ethical Values of Large Language Models
4 Equilibrium Alignment: A Prospective Paradigm for Ethical Value Alignmen


AI for Open Science: A Multi-Agent Perspective for Ethically Translating Data to Knowledge / 2310.18852 / ISBN:https://doi.org/10.48550/arXiv.2310.18852 / Published by ArXiv / on (web) Publishing site
Abstract


LLMs grasp morality in concept / 2311.02294 / ISBN:https://doi.org/10.48550/arXiv.2311.02294 / Published by ArXiv / on (web) Publishing site
3 The Meaning Model


A Brief History of Prompt: Leveraging Language Models. (Through Advanced Prompting) / 2310.04438 / ISBN:https://doi.org/10.48550/arXiv.2310.04438 / Published by ArXiv / on (web) Publishing site
VI. 2015: birth of the transformer
IX. 2019: THE YEAR OF CONTROL
X. 2020-2021: the rise of LLMS


Safety, Trust, and Ethics Considerations for Human-AI Teaming in Aerospace Control / 2311.08943 / ISBN:https://doi.org/10.48550/arXiv.2311.08943 / Published by ArXiv / on (web) Publishing site
III. Safety


Revolutionizing Customer Interactions: Insights and Challenges in Deploying ChatGPT and Generative Chatbots for FAQs / 2311.09976 / ISBN:https://doi.org/10.48550/arXiv.2311.09976 / Published by ArXiv / on (web) Publishing site
6. Open chanllenges
7. Future Research Directions


GPT in Data Science: A Practical Exploration of Model Selection / 2311.11516 / ISBN:https://doi.org/10.48550/arXiv.2311.11516 / Published by ArXiv / on (web) Publishing site
Abstract
III. Approach: capturing and representing heuristics behind GPT's decision-making process
V. Conclusion and future work


Large Language Models in Education: Vision and Opportunities / 2311.13160 / ISBN:https://doi.org/10.48550/arXiv.2311.13160 / Published by ArXiv / on (web) Publishing site
I. Introduction
VI. Challenges and future directions


Towards Auditing Large Language Models: Improving Text-based Stereotype Detection / 2311.14126 / ISBN:https://doi.org/10.48550/arXiv.2311.14126 / Published by ArXiv / on (web) Publishing site
3 Methodology


Ethics and Responsible AI Deployment / 2311.14705 / ISBN:https://doi.org/10.48550/arXiv.2311.14705 / Published by ArXiv / on (web) Publishing site
4. Addressing bias, transparency, and accountability


Survey on AI Ethics: A Socio-technical Perspective / 2311.17228 / ISBN:https://doi.org/10.48550/arXiv.2311.17228 / Published by ArXiv / on (web) Publishing site
Abstract
3 Transparency and explainability


Culturally-Attuned Moral Machines: Implicit Learning of Human Value Systems by AI through Inverse Reinforcement Learning / 2312.17479 / ISBN:https://doi.org/10.48550/arXiv.2312.17479 / Published by ArXiv / on (web) Publishing site
Discussion


Autonomous Threat Hunting: A Future Paradigm for AI-Driven Threat Intelligence / 2401.00286 / ISBN:https://doi.org/10.48550/arXiv.2401.00286 / Published by ArXiv / on (web) Publishing site
Abstract
1. Introduction
4. State-of-the-art AI techniques in autonomous threat hunting
5. Challenges in autonomous threat hunting
9. Conclusion


Exploring the Frontiers of LLMs in Psychological Applications: A Comprehensive Review / 2401.01519 / ISBN:https://doi.org/10.48550/arXiv.2401.01519 / Published by ArXiv / on (web) Publishing site
1. Introduction
7. Challenges and future directions


AI Ethics Principles in Practice: Perspectives of Designers and Developers / 2112.07467 / ISBN:https://doi.org/10.48550/arXiv.2112.07467 / Published by ArXiv / on (web) Publishing site
IV. Results
V. Discussion and suggestions


Unmasking Bias in AI: A Systematic Review of Bias Detection and Mitigation Strategies in Electronic Health Record-based Models / 2310.19917 / ISBN:https://doi.org/10.48550/arXiv.2310.19917 / Published by ArXiv / on (web) Publishing site
Discussion


Resolving Ethics Trade-offs in Implementing Responsible AI / 2401.08103 / ISBN:https://doi.org/10.48550/arXiv.2401.08103 / Published by ArXiv / on (web) Publishing site
I. Introduction


Towards Responsible AI in Banking: Addressing Bias for Fair Decision-Making / 2401.08691 / ISBN:https://doi.org/10.48550/arXiv.2401.08691 / Published by ArXiv / on (web) Publishing site
Contents / List of figures / List of tables / Acronyms
6 FFTree: a flexible tree to mitigate multiple fairness criteria
III Accounting for bias - 7 Addressing fairness in the banking sector
8 Fairview: an evaluative AI support for addressing fairness


FAIR Enough How Can We Develop and Assess a FAIR-Compliant Dataset for Large Language Models' Training? / 2401.11033 / ISBN:https://doi.org/10.48550/arXiv.2401.11033 / Published by ArXiv / on (web) Publishing site
1 Introduction
5 Discussion
6 Conclusion


Beyond principlism: Practical strategies for ethical AI use in research practices / 2401.15284 / ISBN:https://doi.org/10.48550/arXiv.2401.15284 / Published by ArXiv / on (web) Publishing site
3 Five specific goals and action-guiding strategies for ethical AI use in research practices


A Scoping Study of Evaluation Practices for Responsible AI Tools: Steps Towards Effectiveness Evaluations / 2401.17486 / ISBN:https://doi.org/10.48550/arXiv.2401.17486 / Published by ArXiv / on (web) Publishing site
4 RAI tool evaluation practices
A List of RAI tools, with their primary publication
C List of publications, with their associated RAI tools
D Summary of themes and codes


Detecting Multimedia Generated by Large AI Models: A Survey / 2402.00045 / ISBN:https://doi.org/10.48550/arXiv.2402.00045 / Published by ArXiv / on (web) Publishing site
Abstract
3 Detection
5 Discussion


(A)I Am Not a Lawyer, But...: Engaging Legal Experts towards Responsible LLM Policies for Legal Advice / 2402.01864 / ISBN:https://doi.org/10.48550/arXiv.2402.01864 / Published by ArXiv / on (web) Publishing site
2 Related work and our approach


Ethics in AI through the Practitioner's View: A Grounded Theory Literature Review / 2206.09514 / ISBN:https://doi.org/10.48550/arXiv.2206.09514 / Published by ArXiv / on (web) Publishing site
4 Challenges, Threats and Limitations


Generative Artificial Intelligence in Healthcare: Ethical Considerations and Assessment Checklist / 2311.02107 / ISBN:https://doi.org/10.48550/arXiv.2311.02107 / Published by ArXiv / on (web) Publishing site
Appendix


Mapping the Ethics of Generative AI: A Comprehensive Scoping Review / 2402.08323 / ISBN:https://doi.org/10.48550/arXiv.2402.08323 / Published by ArXiv / on (web) Publishing site
3 Results


Taking Training Seriously: Human Guidance and Management-Based Regulation of Artificial Intelligence / 2402.08466 / ISBN:https://doi.org/10.48550/arXiv.2402.08466 / Published by ArXiv / on (web) Publishing site
1 Introduction
4 Techniques of Human-Guided Training
5 Advantages of Human-Guided Training
6 Limitations


User Modeling and User Profiling: A Comprehensive Survey / 2402.09660 / ISBN:https://doi.org/10.48550/arXiv.2402.09660 / Published by ArXiv / on (web) Publishing site
1 Introduction
3 Paradigm Shifts and New Trends
4 Current Taxonomy


The METRIC-framework for assessing data quality for trustworthy AI in medicine: a systematic review / 2402.13635 / ISBN:https://doi.org/10.48550/arXiv.2402.13635 / Published by ArXiv / on (web) Publishing site
Abstract
Introduction
Discussion


The European Commitment to Human-Centered Technology: The Integral Role of HCI in the EU AI Act's Success / 2402.14728 / ISBN:https://doi.org/10.48550/arXiv.2402.14728 / Published by ArXiv / on (web) Publishing site
2 The EU AI Act


Implications of Regulations on the Use of AI and Generative AI for Human-Centered Responsible Artificial Intelligence / 2403.00148 / ISBN:https://doi.org/10.48550/arXiv.2403.00148 / Published by ArXiv / on (web) Publishing site
1 Motivation & Background


The Minimum Information about CLinical Artificial Intelligence Checklist for Generative Modeling Research (MI-CLAIM-GEN) / 2403.02558 / ISBN:https://doi.org/10.48550/arXiv.2403.02558 / Published by ArXiv / on (web) Publishing site
Abstract
Part 5. Interpretability of generative models
Conclusions
Table 1. Updated MI-CLAIM checklist for generative AI clinical studies.


Towards an AI-Enhanced Cyber Threat Intelligence Processing Pipeline / 2403.03265 / ISBN:https://doi.org/10.48550/arXiv.2403.03265 / Published by ArXiv / on (web) Publishing site
Abstract
II. Background & Literature Review
IV. Challenges and Considerations
V. Conclusions & Future Research


A Survey on Human-AI Teaming with Large Pre-Trained Models / 2403.04931 / ISBN:https://doi.org/10.48550/arXiv.2403.04931 / Published by ArXiv / on (web) Publishing site
2 AI Model Improvements with Human-AI Teaming


AGI Artificial General Intelligence for Education / 2304.12479 / ISBN:https://doi.org/10.48550/arXiv.2304.12479 / Published by ArXiv / on (web) Publishing site
2. What is AGI
4. Ethical Issues and Concerns
5. Discussion


Responsible Artificial Intelligence: A Structured Literature Review / 2403.06910 / ISBN:https://doi.org/10.48550/arXiv.2403.06910 / Published by ArXiv / on (web) Publishing site
3. Analysis


Review of Generative AI Methods in Cybersecurity / 2403.08701 / ISBN:https://doi.org/10.48550/arXiv.2403.08701 / Published by ArXiv / on (web) Publishing site
4 Cyber Defence


Trust in AI: Progress, Challenges, and Future Directions / 2403.14680 / ISBN:https://doi.org/10.48550/arXiv.2403.14680 / Published by ArXiv / on (web) Publishing site
1. Introduction
2. Methodology
3. Findings
4. Discussion
5. Concluding Remarks and Future Directions


Safeguarding Marketing Research: The Generation, Identification, and Mitigation of AI-Fabricated Disinformation / 2403.14706 / ISBN:https://doi.org/10.48550/arXiv.2403.14706 / Published by ArXiv / on (web) Publishing site
Methodology
Results


The Journey to Trustworthy AI- Part 1 Pursuit of Pragmatic Frameworks / 2403.15457 / ISBN:https://doi.org/10.48550/arXiv.2403.15457 / Published by ArXiv / on (web) Publishing site
2 Trustworthy AI Too Many Definitions or Lack Thereof?
7 Explainable AI as an Enabler of Trustworthy AI


Exploring the Nexus of Large Language Models and Legal Systems: A Short Survey / 2404.00990 / ISBN:https://doi.org/10.48550/arXiv.2404.00990 / Published by ArXiv / on (web) Publishing site
Abstract
1 Introduction
6 Conclusion and Future Directions


The Pursuit of Fairness in Artificial Intelligence Models A Survey / 2403.17333 / ISBN:https://doi.org/10.48550/arXiv.2403.17333 / Published by ArXiv / on (web) Publishing site
A Appendices


A Critical Survey on Fairness Benefits of Explainable AI / 2310.13007 / ISBN:https://doi.org/10.1145/3630106.3658990 / Published by ArXiv / on (web) Publishing site
3 Methodology
4 Critical Survey


AI Alignment: A Comprehensive Survey / 2310.19852 / ISBN:https://doi.org/10.48550/arXiv.2310.19852 / Published by ArXiv / on (web) Publishing site
Abstract
1 Introduction
2 Learning from Feedback
3 Learning under Distribution Shift
4 Assurance
5 Governance
6 Conclusion


Large Language Model Supply Chain: A Research Agenda / 2404.12736 / ISBN:https://doi.org/10.48550/arXiv.2404.12736 / Published by ArXiv / on (web) Publishing site
Abstract
4 LLM Lifecycle


From Model Performance to Claim: How a Change of Focus in Machine Learning Replicability Can Help Bridge the Responsibility Gap / 2404.13131 / ISBN:https://doi.org/10.1145/3630106.3658951 / Published by ArXiv / on (web) Publishing site
2 Disentangling Replicability of Model Performance Claiim and Replicability of Social Claim


Not a Swiss Army Knife: Academics' Perceptions of Trade-Offs Around Generative Artificial Intelligence Use / 2405.00995 / ISBN:https://doi.org/10.48550/arXiv.2405.00995 / Published by ArXiv / on (web) Publishing site
2 Related Work


Towards an Ethical and Inclusive Implementation of Artificial Intelligence in Organizations: A Multidimensional Framework / 2405.01697 / ISBN:https://doi.org/10.48550/arXiv.2405.01697 / Published by ArXiv / on (web) Publishing site
2 How can organizations participate


A Survey on Large Language Models for Critical Societal Domains: Finance, Healthcare, and Law / 2405.01769 / ISBN:https://doi.org/10.48550/arXiv.2405.01769 / Published by ArXiv / on (web) Publishing site
2 Related Surveys
4 Medicine and Healthcare
6 Ethics


Responsible AI: Portraits with Intelligent Bibliometrics / 2405.02846 / ISBN:https://doi.org/10.48550/arXiv.2405.02846 / Published by ArXiv / on (web) Publishing site
IV. Bibliometric Portraits of Responsible AI


Exploring the Potential of the Large Language Models (LLMs) in Identifying Misleading News Headlines / 2405.03153 / ISBN:https://doi.org/10.48550/arXiv.2405.03153 / Published by ArXiv / on (web) Publishing site
5 Discussion


Guiding the Way: A Comprehensive Examination of AI Guidelines in Global Media / 2405.04706 / ISBN:https://doi.org/10.48550/arXiv.2405.04706 / Published by ArXiv / on (web) Publishing site
3 Data and Methods


RAI Guidelines: Method for Generating Responsible AI Guidelines Grounded in Regulations and Usable by (Non-)Technical Roles / 2307.15158 / ISBN:https://doi.org/10.48550/arXiv.2307.15158 / Published by ArXiv / on (web) Publishing site
4 Method for Generating Responsible AI Guidelines


Redefining Qualitative Analysis in the AI Era: Utilizing ChatGPT for Efficient Thematic Analysis / 2309.10771 / ISBN:https://doi.org/10.48550/arXiv.2309.10771 / on (web) Publishing site
2 Related Work
4 Users’ Experiences and Challenges with ChatGPT
5 Analyses of the Design Process
6 User’s Attitude on ChatGPT’s Qualitative Analysis Assistance: from no to yes
7 Discussion


A scoping review of using Large Language Models (LLMs) to investigate Electronic Health Records (EHRs) / 2405.03066 / ISBN:https://doi.org/10.48550/arXiv.2405.03066 / Published by ArXiv / on (web) Publishing site
2 Materials
3 Results


Integrating Emotional and Linguistic Models for Ethical Compliance in Large Language Models / 2405.07076 / ISBN:https://doi.org/10.48550/arXiv.2405.07076 / Published by ArXiv / on (web) Publishing site
3 Quantitative Models of Emotions, Behaviors, and Ethics


Using ChatGPT for Thematic Analysis / 2405.08828 / ISBN:https://doi.org/10.48550/arXiv.2405.08828 / Published by ArXiv / on (web) Publishing site
4 Validation Using Topic Modeling


The Narrow Depth and Breadth of Corporate Responsible AI Research / 2405.12193 / ISBN:https://doi.org/10.48550/arXiv.2405.12193 / Published by ArXiv / on (web) Publishing site
S1 Additional Analyses on Engagement Analysis


A Comprehensive Overview of Large Language Models (LLMs) for Cyber Defences: Opportunities and Directions / 2405.14487 / ISBN:https://doi.org/10.48550/arXiv.2405.14487 / Published by ArXiv / on (web) Publishing site
VII. Cyber Security Operations Automation


Deception Analysis with Artificial Intelligence: An Interdisciplinary Perspective / 2406.05724 / ISBN:https://doi.org/10.48550/arXiv.2406.05724 / Published by ArXiv / on (web) Publishing site
3 Reductionism & Previous Research in Deceptive AI


The Ethics of Interaction: Mitigating Security Threats in LLMs / 2401.12273 / ISBN:https://doi.org/10.48550/arXiv.2401.12273 / Published by ArXiv / on (web) Publishing site
2 Why Ethics Matter in LLM Attacks?


Global AI Governance in Healthcare: A Cross-Jurisdictional Regulatory Analysis / 2406.08695 / ISBN:https://doi.org/10.48550/arXiv.2406.08695 / Published by ArXiv / on (web) Publishing site
4 Global Regulatory Landscape of AI


Applications of Generative AI in Healthcare: algorithmic, ethical, legal and societal considerations / 2406.10632 / ISBN:https://doi.org/10.48550/arXiv.2406.10632 / Published by ArXiv / on (web) Publishing site
III. Analysis
Appendix B Legal aspects
Appendix C Algorithmic / technical aspects


Current state of LLM Risks and AI Guardrails / 2406.12934 / ISBN:https://doi.org/10.48550/arXiv.2406.12934 / Published by ArXiv / on (web) Publishing site
2 Large Language Model Risks


Leveraging Large Language Models for Patient Engagement: The Power of Conversational AI in Digital Health / 2406.13659 / ISBN:https://doi.org/10.48550/arXiv.2406.13659 / Published by ArXiv / on (web) Publishing site
I. INTRODUCTION
IV. DISCUSSION AND F UTURE D IRECTIONS


AI Alignment through Reinforcement Learning from Human Feedback? Contradictions and Limitations / 2406.18346 / ISBN:https://doi.org/10.48550/arXiv.2406.18346 / Published by ArXiv / on (web) Publishing site
Abstract


A Survey on Privacy Attacks Against Digital Twin Systems in AI-Robotics / 2406.18812 / ISBN:https://doi.org/10.48550/arXiv.2406.18812 / Published by ArXiv / on (web) Publishing site
IV. DT-INTEGRATED ROBOTICS DESIGN CONSIDERATIONS AND DISCUSSION


Why should we ever automate moral decision making? / 2407.07671 / ISBN:https://doi.org/10.48550/arXiv.2407.07671 / Published by ArXiv / on (web) Publishing site
2 Reasons for automated moral decision making


Bridging the Global Divide in AI Regulation: A Proposal for a Contextual, Coherent, and Commensurable Framework / 2303.11196 / ISBN:https://doi.org/10.48550/arXiv.2303.11196 / Published by ArXiv / on (web) Publishing site
IV. Proposing an Alternative 3C Framework
V. Conclusion


CogErgLLM: Exploring Large Language Model Systems Design Perspective Using Cognitive Ergonomics / 2407.02885 / ISBN:https://doi.org/10.48550/arXiv.2407.02885 / Published by ArXiv / on (web) Publishing site
6 Discussion


Thorns and Algorithms: Navigating Generative AI Challenges Inspired by Giraffes and Acacias / 2407.11360 / ISBN:https://doi.org/10.48550/arXiv.2407.11360 / Published by ArXiv / on (web) Publishing site
4 Generative AI and Humans: Risks and Mitigation


Report on the Conference on Ethical and Responsible Design in the National AI Institutes: A Summary of Challenges / 2407.13926 / ISBN:https://doi.org/10.48550/arXiv.2407.13926 / Published by ArXiv / on (web) Publishing site
3. AI Institutes and Society


Improving Large Language Model (LLM) fidelity through context-aware grounding: A systematic approach to reliability and veracity / 2408.04023 / ISBN:https://doi.org/10.48550/arXiv.2408.04023 / Published by ArXiv / on (web) Publishing site
Abstract
1. Introduction
3. Proposed framework
7. Conclusion and Future Directions


Criticizing Ethics According to Artificial Intelligence / 2408.04609 / ISBN:https://doi.org/10.48550/arXiv.2408.04609 / Published by ArXiv / on (web) Publishing site
1 Preliminary notes


Recent Advances in Generative AI and Large Language Models: Current Status, Challenges, and Perspectives / 2407.14962 / ISBN:https://doi.org/10.48550/arXiv.2407.14962 / Published by ArXiv / on (web) Publishing site
Abstract
IV. Challenges of Generative AI and LLMs
V. Bridging Research Gaps and Future Directions


Neuro-Symbolic AI for Military Applications / 2408.09224 / ISBN:https://doi.org/10.48550/arXiv.2408.09224 / Published by ArXiv / on (web) Publishing site
Abstract
I. Introduction
II. Neuro-Symbolic AI
III. Autonomy in Military Weapons Systems
VI. Interpretability and Explainability


Catalog of General Ethical Requirements for AI Certification / 2408.12289 / ISBN:https://doi.org/10.48550/arXiv.2408.12289 / Published by ArXiv / on (web) Publishing site
10 Transparency and Explainability (T)


Dataset | Mindset = Explainable AI | Interpretable AI / 2408.12420 / ISBN:https://doi.org/10.48550/arXiv.2408.12420 / Published by ArXiv / on (web) Publishing site
1. Introduction


Has Multimodal Learning Delivered Universal Intelligence in Healthcare? A Comprehensive Survey / 2408.12880 / ISBN:https://doi.org/10.48550/arXiv.2408.12880 / Published by ArXiv / on (web) Publishing site
3 Multimodal Medical Studies
7 Challenges and Future Directions


Trustworthy and Responsible AI for Human-Centric Autonomous Decision-Making Systems / 2408.15550 / ISBN:https://doi.org/10.48550/arXiv.2408.15550 / Published by ArXiv / on (web) Publishing site
Abstract
1 Introduction
2 Trustworthy and Responsible AI Definition
5 Trustworthy and Responsible AI in Human-centric Applications
6 Open Challenges


A Survey for Large Language Models in Biomedicine / 2409.00133 / ISBN:https://doi.org/10.48550/arXiv.2409.00133 / Published by ArXiv / on (web) Publishing site
Abstract
4 Adapting General LLMs to the Biomedical Field
5 Discussion
6 Conclusion


Digital Homunculi: Reimagining Democracy Research with Generative Agents / 2409.00826 / ISBN:https://doi.org/10.48550/arXiv.2409.00826 / Published by ArXiv / on (web) Publishing site
5. Annoyances or Dealbreakers?


The overlooked need for Ethics in Complexity Science: Why it matters / 2409.02002 / ISBN:https://doi.org/10.48550/arXiv.2409.02002 / Published by ArXiv / on (web) Publishing site
Annexus


Artificial intelligence to advance Earth observation: : A review of models, recent trends, and pathways forward / 2305.08413 / ISBN:https://doi.org/10.48550/arXiv.2305.08413 / Published by ArXiv / on (web) Publishing site
4 Explainable AI and causal inference
5 Physics-aware machine learning


Navigating LLM Ethics: Advancements, Challenges, and Future Directions / 2406.18841 / ISBN:https://doi.org/10.48550/arXiv.2406.18841 / Published by ArXiv / on (web) Publishing site
V. Discussion


How Mature is Requirements Engineering for AI-based Systems? A Systematic Mapping Study on Practices, Challenges, and Future Research Directions / 2409.07192 / ISBN:https://doi.org/10.48550/arXiv.2409.07192 / Published by ArXiv / on (web) Publishing site
4 Results
5 Open Challenges and Future Research Directions (RQ5)
6 Discussions


ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMs / 2409.09586 / ISBN:https://doi.org/10.48550/arXiv.2409.09586 / Published by ArXiv / on (web) Publishing site
2 Related Work


Artificial Human Intelligence: The role of Humans in the Development of Next Generation AI / 2409.16001 / ISBN:https://doi.org/10.48550/arXiv.2409.16001 / Published by ArXiv / on (web) Publishing site
IV. Human-Level AI and Challenges/Perspectives
V. Final Thoughts and Discussion


Ethical and Scalable Automation: A Governance and Compliance Framework for Business Applications / 2409.16872 / ISBN:https://doi.org/10.48550/arXiv.2409.16872 / Published by ArXiv / on (web) Publishing site
2. Literature Review


Decoding Large-Language Models: A Systematic Overview of Socio-Technical Impacts, Constraints, and Emerging Questions / 2409.16974 / ISBN:https://doi.org/10.48550/arXiv.2409.16974 / Published by ArXiv / on (web) Publishing site
7 Limitations & Considerations (RQ3)
8 Discussion


Do LLMs Have Political Correctness? Analyzing Ethical Biases and Jailbreak Vulnerabilities in AI Systems / 2410.13334 / ISBN:https://doi.org/10.48550/arXiv.2410.13334 / Published by ArXiv / on (web) Publishing site
3 Methodology PCJAILBREAK


Trustworthy XAI and Application / 2410.17139 / ISBN:https://doi.org/10.48550/arXiv.2410.17139 / Published by ArXiv / on (web) Publishing site
1 Introduction
3 Applications of XAI
4 Future of Trustworthy (XAI)


Standardization Trends on Safety and Trustworthiness Technology for Advanced AI / 2410.22151 / ISBN:https://doi.org/10.48550/arXiv.2410.22151 / Published by ArXiv / on (web) Publishing site
3 Trends in advanced AI safety and trustworthiness standardization


Democratizing Reward Design for Personal and Representative Value-Alignment / 2410.22203 / ISBN:https://doi.org/10.48550/arXiv.2410.22203 / Published by ArXiv / on (web) Publishing site
2 Background and Related Work


How should AI decisions be explained? Requirements for Explanations from the Perspective of European Law / 2404.12762 / ISBN:https://doi.org/10.48550/arXiv.2404.12762 / Published by ArXiv / on (web) Publishing site
2 Related Work


A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directions / 2406.03712 / ISBN:https://doi.org/10.48550/arXiv.2406.03712 / Published by ArXiv / on (web) Publishing site
I. Introduction
V. Applying Medical LLMs
VI. Trustworthiness and Safety
VII. Future Directions


Collaborative Participatory Research with LLM Agents in South Asia: An Empirically-Grounded Methodological Initiative and Agenda from Field Evidence in Sri Lanka / 2411.08294 / ISBN:https://doi.org/10.48550/arXiv.2411.08294 / Published by ArXiv / on (web) Publishing site
3 Proposed LLM4Participatory Research Framework


Bias in Large Language Models: Origin, Evaluation, and Mitigation / 2411.10915 / ISBN:https://doi.org/10.48550/arXiv.2411.10915 / Published by ArXiv / on (web) Publishing site
4. Bias Evaluation


Privacy-Preserving Video Anomaly Detection: A Survey / 2411.14565 / ISBN:https://doi.org/10.48550/arXiv.2411.14565 / Published by ArXiv / on (web) Publishing site
Abstract
I. Introduction
VII. Discussion


Artificial Intelligence Policy Framework for Institutions / 2412.02834 / ISBN:https://doi.org/10.48550/arXiv.2412.02834 / Published by ArXiv / on (web) Publishing site
Abstract
III. Key Considerations for AI Policy
IV. Framework for AI Policy Development


Ethical Challenges and Evolving Strategies in the Integration of Artificial Intelligence into Clinical Practice / 2412.03576 / ISBN:https://doi.org/10.48550/arXiv.2412.03576 / Published by ArXiv / on (web) Publishing site
Introduction and Motivation
Core Ethical Challenges


Large Language Models in Politics and Democracy: A Comprehensive Survey / 2412.04498 / ISBN:https://doi.org/10.48550/arXiv.2412.04498 / Published by ArXiv / on (web) Publishing site
3. LLM Applications in Politics


From Principles to Practice: A Deep Dive into AI Ethics and Regulations / 2412.04683 / ISBN:https://doi.org/10.48550/arXiv.2412.04683 / Published by ArXiv / on (web) Publishing site
II AI Practice and Contextual Integrity
IV Integrative AI Ethics


Technology as uncharted territory: Contextual integrity and the notion of AI as new ethical ground / 2412.05130 / ISBN:https://doi.org/10.48550/arXiv.2412.05130 / Published by ArXiv / on (web) Publishing site
II AI Practice and Contextual Integrity
IV Integrative AI Ethics


Political-LLM: Large Language Models in Political Science / 2412.06864 / ISBN:https://doi.org/10.48550/arXiv.2412.06864 / Published by ArXiv / on (web) Publishing site
1 Introduction
4 Classical Political Science Functions and Modern Transformations
5 Technical Foundations for LLM Applications in Political Science
6 Future Directions & Challenges


Trustworthy artificial intelligence in the energy sector: Landscape analysis and evaluation framework / 2412.07782 / ISBN:https://doi.org/10.48550/arXiv.2412.07782 / Published by ArXiv / on (web) Publishing site
III. E-TAI – Methodological Framework for Trustworthy AI in the Energy Domain


Digital Democracy in the Age of Artificial Intelligence / 2412.07791 / ISBN:https://doi.org/10.48550/arXiv.2412.07791 / Published by ArXiv / on (web) Publishing site
4. Representation: Digital and AI Technologies in Modern Electoral Processes


Large Language Model Safety: A Holistic Survey / 2412.17686 / ISBN:https://doi.org/10.48550/arXiv.2412.17686 / Published by ArXiv / on (web) Publishing site
Abstract
1 Introduction
2 Taxonomy
4 Robustness to Attack
8 Interpretability for LLM Safety
9 Technology Roadmaps / Strategies to LLM Safety in Practice
10 Governance
12 Conclusion


Hybrid Approaches for Moral Value Alignment in AI Agents: a Manifesto / 2312.01818 / ISBN:https://doi.org/10.48550/arXiv.2312.01818 / Published by ArXiv / on (web) Publishing site
1. Introduction
3. Designing AI Agents based on Moral Principles


Addressing Intersectionality, Explainability, and Ethics in AI-Driven Diagnostics: A Rebuttal and Call for Transdiciplinary Action / 2501.08497 / ISBN:https://doi.org/10.48550/arXiv.2501.08497 / Published by ArXiv / on (web) Publishing site
Abstract
5 The Ethical Role of Engineers in AI Development


Towards A Litmus Test for Common Sense / 2501.09913 / ISBN:https://doi.org/10.48550/arXiv.2501.09913 / Published by ArXiv / on (web) Publishing site
9 Open Challenges and Future Work


Uncovering Bias in Foundation Models: Impact, Testing, Harm, and Mitigation / 2501.10453 / ISBN:https://doi.org/10.48550/arXiv.2501.10453 / Published by ArXiv / on (web) Publishing site
1 Introduction
Supplementary


Development of Application-Specific Large Language Models to Facilitate Research Ethics Review / 2501.10741 / ISBN:https://doi.org/10.48550/arXiv.2501.10741 / Published by ArXiv / on (web) Publishing site
III. Generative AI for IRB review


The Third Moment of AI Ethics: Developing Relatable and Contextualized Tools / 2501.16954 / ISBN:https://doi.org/10.48550/arXiv.2501.16954 / Published by ArXiv / on (web) Publishing site
Appendices


Ethical Considerations for the Military Use of Artificial Intelligence in Visual Reconnaissance / 2502.03376 / ISBN:https://doi.org/10.48550/arXiv.2502.03376 / Published by ArXiv / on (web) Publishing site
2 Principles of Ethical AI
5 Use Case 3 - Land-based Reconnaissance in Inhabited Area


Safety at Scale: A Comprehensive Survey of Large Model Safety / 2502.05206 / ISBN:https://doi.org/10.48550/arXiv.2502.05206 / Published by ArXiv / on (web) Publishing site
2 Vision Foundation Model Safety


Integrating Generative Artificial Intelligence in ADRD: A Framework for Streamlining Diagnosis and Care in Neurodegenerative Diseases / 2502.06842 / ISBN:https://doi.org/10.48550/arXiv.2502.06842 / Published by ArXiv / on (web) Publishing site
High Quality Data Collection


Fairness in Multi-Agent AI: A Unified Framework for Ethical and Equitable Autonomous Systems / 2502.07254 / ISBN:https://doi.org/10.48550/arXiv.2502.07254 / Published by ArXiv / on (web) Publishing site
Paper


Agentic AI: Expanding the Algorithmic Frontier of Creative Problem Solving / 2502.00289 / ISBN:https://doi.org/10.48550/arXiv.2502.00289 / Published by ArXiv / on (web) Publishing site
Liability, Consent, and Accountability


From large language models to multimodal AI: A scoping review on the potential of generative AI in medicine / 2502.09242 / ISBN:https://doi.org/10.48550/arXiv.2502.09242 / Published by ArXiv / on (web) Publishing site
Abstract
7 Discussion


AI and the Transformation of Accountability and Discretion in Urban Governance / 2502.13101 / ISBN:https://doi.org/10.48550/arXiv.2502.13101 / Published by ArXiv / on (web) Publishing site
4. Guiding Principles for AI-Enhanced Governance in Urban Policy


Multi-Agent Risks from Advanced AI / 2502.14143 / ISBN:https://doi.org/10.48550/arXiv.2502.14143 / Published by ArXiv / on (web) Publishing site
1 Introduction
2 Failure Modes
3 Risk Factors
4 Implications


On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective / 2502.14296 / ISBN:https://doi.org/10.48550/arXiv.2502.14296 / Published by ArXiv / on (web) Publishing site
2 Background
7 Benchmarking Vision-Language Models
9 Trustworthiness in Downstream Applications
10 Further Discussion


Surgical Scene Understanding in the Era of Foundation AI Models: A Comprehensive Review / 2502.14886 / ISBN:https://doi.org/10.48550/arXiv.2502.14886 / Published by ArXiv / on (web) Publishing site
II. Background and Challenges
V. ML/DL Applications in Surgical Training and Simulation
VI. Open Issues and Future Research Directions in Surgical Scene Understanding


Comprehensive Analysis of Transparency and Accessibility of ChatGPT, DeepSeek, And other SoTA Large Language Models / 2502.18505 / ISBN:https://doi.org/10.48550/arXiv.2502.18505 / Published by ArXiv / on (web) Publishing site
2. Methodology


Evaluating Large Language Models on the Spanish Medical Intern Resident (MIR) Examination 2024/2025:A Comparative Analysis of Clinical Reasoning and Knowledge Application / 2503.00025 / ISBN:https://doi.org/10.48550/arXiv.2503.00025 / Published by ArXiv / on (web) Publishing site
5. Conclusion


Can AI Model the Complexities of Human Moral Decision-Making? A Qualitative Study of Kidney Allocation Decisions / 2503.00940 / ISBN:https://doi.org/10.48550/arXiv.2503.00940 / Published by ArXiv / on (web) Publishing site
2 Related Work
5 Discussion


Vision Language Models in Medicine / 2503.01863 / ISBN:https://doi.org/10.48550/arXiv.2503.01863 / Published by ArXiv / on (web) Publishing site
Abstract
V. Challenges and Limitations
VI. Opportunities and Future Directions


Medical Hallucinations in Foundation Models and Their Impact on Healthcare / 2503.05777 / ISBN:https://doi.org/10.48550/arXiv.2503.05777 / Published by ArXiv / on (web) Publishing site
2 LLM Hallucinations in Medicine
5 Mitigation Strategies
8 Survey on AI/LLM Adoption and Medical Hallucinations Among Healthcare Professionals and Researchers


Generative AI in Transportation Planning: A Survey / 2503.07158 / ISBN:https://doi.org/10.48550/arXiv.2503.07158 / Published by ArXiv / on (web) Publishing site
2 Background
3 Classical Transportation Planning Functions and Modern Transformations
5 Future Directions & Challenges


Detecting Dataset Bias in Medical AI: A Generalized and Modality-Agnostic Auditing Framework / 2503.09969 / ISBN:https://doi.org/10.48550/arXiv.2503.09969 / Published by ArXiv / on (web) Publishing site
2 Results


LLMs in Disease Diagnosis: A Comparative Study of DeepSeek-R1 and O3 Mini Across Chronic Health Conditions / 2503.10486 / ISBN:https://doi.org/10.48550/arXiv.2503.10486 / Published by ArXiv / on (web) Publishing site
Abstract
2 Related Work
3 Methodology
5 Discussion


Synthetic Data for Robust AI Model Development in Regulated Enterprises / 2503.12353 / ISBN:https://doi.org/10.48550/arXiv.2503.12353 / Published by ArXiv / on (web) Publishing site
Challenges and Limitations
Future Directions


Policy Frameworks for Transparent Chain-of-Thought Reasoning in Large Language Models / 2503.14521 / ISBN:https://doi.org/10.48550/arXiv.2503.14521 / Published by ArXiv / on (web) Publishing site
1 Motivation


The Role of Legal Frameworks in Shaping Ethical Artificial Intelligence Use in Corporate Governance / 2503.14540 / ISBN:https://doi.org/10.48550/arXiv.2503.14540 / Published by ArXiv / on (web) Publishing site
II. Legal Frameworks and Corporate AI Governance: Current Landscape and Emerging Approaches
III. Conclusion


A Peek Behind the Curtain: Using Step-Around Prompt Engineering to Identify Bias and Misinformation in GenAI Models / 2503.15205 / ISBN:https://doi.org/10.48550/arXiv.2503.15205 / Published by ArXiv / on (web) Publishing site
Step-Around Prompting: A Research Tool and Potential Threat
Discussion and Recommendations


Advancing Human-Machine Teaming: Concepts, Challenges, and Applications / 2503.16518 / ISBN:https://doi.org/10.48550/arXiv.2503.16518 / Published by ArXiv / on (web) Publishing site
3 Empirical Studies to Promote Team Performance


HH4AI: A methodological Framework for AI Human Rights impact assessment under the EUAI ACT / 2503.18994 / ISBN:https://doi.org/10.48550/arXiv.2503.18994 / Published by ArXiv / on (web) Publishing site
3 Standards and Guidelines


AI Identity, Empowerment, and Mindfulness in Mitigating Unethical AI Use / 2503.20099 / ISBN:https://doi.org/10.48550/arXiv.2503.20099 / Published by ArXiv / on (web) Publishing site
Introduction
Literature Review


AI Family Integration Index (AFII): Benchmarking a New Global Readiness for AI as Family / 2503.22772 / ISBN:https://doi.org/10.48550/arXiv.2503.22772 / Published by ArXiv / on (web) Publishing site
Abstract
2. Research Methodology
4. AI-Family Integration (AFI) – Benchmarking with AI Policy Penetration and Traditional AI Index


Bridging the Gap: Integrating Ethics and Environmental Sustainability in AI Research and Practice / 2504.00797 / ISBN:https://doi.org/10.48550/arXiv.2504.00797 / Published by ArXiv / on (web) Publishing site
3 Existing Scholarship in AI Ethics and Sustainability
4 Transversal Issues in AI Ethics and Sustainability


Systematic Literature Review: Explainable AI Definitions and Challenges in Education / 2504.02910 / ISBN:https://doi.org/10.48550/arXiv.2504.02910 / Published by ArXiv / on (web) Publishing site
Methodology
Explainability (CH1)
Trustworthy (CH5)
Discussion


Automating the Path: An R&D Agenda for Human-Centered AI and Visualization / 2504.07529 / ISBN:https://doi.org/10.48550/arXiv.2504.07529 / Published by ArXiv / on (web) Publishing site
Background
Updating the R&D Agenda


AI-Driven Healthcare: A Review on Ensuring Fairness and Mitigating Bias / 2407.19655 / ISBN:https://doi.org/10.48550/arXiv.2407.19655 / Published by ArXiv / on (web) Publishing site
4 Research gaps and Future directions


A Comprehensive Survey on Integrating Large Language Models with Knowledge-Based Methods / 2501.13947 / ISBN:https://doi.org/10.48550/arXiv.2501.13947 / Published by ArXiv / on (web) Publishing site
1. Introduction
3. Challenges in implementing LLMs for real-world scenarios
4. Solutions to address LLM challenges
5. Integrating LLMs with knowledge bases


An Empirical Study on Decision-Making Aspects in Responsible Software Engineering for AI / 2501.15691 / ISBN:https://doi.org/10.48550/arXiv.2501.15691 / Published by ArXiv / on (web) Publishing site
IV. Results and Analysis


Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation / 2502.05151 / ISBN:https://doi.org/10.48550/arXiv.2502.05151 / Published by ArXiv / on (web) Publishing site
3 AI Support for Individual Topics and Tasks


Who is Responsible? The Data, Models, Users or Regulations? A Comprehensive Survey on Responsible Generative AI for a Sustainable Future / 2502.08650 / ISBN:https://doi.org/10.48550/arXiv.2502.08650 / Published by ArXiv / on (web) Publishing site
2 Responsible Generative AI
3 Explainable AI
4 Best Practices for Responsible Generative AI and Existing Frameworks
6 Discussion


Confirmation Bias in Generative AI Chatbots: Mechanisms, Risks, Mitigation Strategies, and Future Research Directions / 2504.09343 / ISBN:https://doi.org/10.48550/arXiv.2504.09343 / Published by ArXiv / on (web) Publishing site
1. Introduction
7. Future Research Directions


Framework, Standards, Applications and Best practices of Responsible AI : A Comprehensive Survey / 2504.13979 / ISBN:https://doi.org/10.48550/arXiv.2504.13979 / Published by ArXiv / on (web) Publishing site
2. Trustworthy AI Framework
6. Applications of RAI


Towards responsible AI for education: Hybrid human-AI to confront the Elephant in the room / 2504.16148 / ISBN:https://doi.org/10.48550/arXiv.2504.16148 / Published by ArXiv / on (web) Publishing site
3. Challenges of current AI methods in education: The Elephant in the room
4. Hybrid human-AI methods for responsible AI for education


Auditing the Ethical Logic of Generative AI Models / 2504.17544 / ISBN:https://doi.org/10.48550/arXiv.2504.17544 / Published by ArXiv / on (web) Publishing site
Seven Contemporary LLMs


AI Ethics and Social Norms: Exploring ChatGPT's Capabilities From What to How / 2504.18044 / ISBN:https://doi.org/10.48550/arXiv.2504.18044 / Published by ArXiv / on (web) Publishing site
3 Methodology
5 Discussion


A Design Framework for operationalizing Trustworthy Artificial Intelligence in Healthcare: Requirements, Tradeoffs and Challenges for its Clinical Adoption / 2504.19179 / ISBN:https://doi.org/10.48550/arXiv.2504.19179 / Published by ArXiv / on (web) Publishing site
4. Design framework for medical AI systems
5. Tradeoffs between TAI principles and requirements
6. Challenges towards the practical adoption of the design framework in healthcare


Towards responsible AI for education: Hybrid human-AI to confront the Elephant in the room / 2504.16148 / ISBN:https://doi.org/10.48550/arXiv.2504.16148 / Published by ArXiv / on (web) Publishing site
3 Evaluating AI Awareness in LLMs
4 AI Awareness and AI Capabilities


AI Awareness / 2504.20084 / ISBN:https://doi.org/10.48550/arXiv.2504.20084 / Published by ArXiv / on (web) Publishing site
3 Evaluating AI Awareness in LLMs
4 AI Awareness and AI Capabilities


From Texts to Shields: Convergence of Large Language Models and Cybersecurity / 2505.00841 / ISBN:https://doi.org/10.48550/arXiv.2505.00841 / Published by ArXiv / on (web) Publishing site
Abstract
3 LLM Agent and Applications
5 LLM Interpretability, Safety, and Security
6 Conclusion
Appendices


Emotions in the Loop: A Survey of Affective Computing for Emotional Support / 2505.01542 / ISBN:https://doi.org/10.48550/arXiv.2505.01542 / Published by ArXiv / on (web) Publishing site
IV. Applications and Approaches


Ethical AI in the Healthcare Sector: Investigating Key Drivers of Adoption through the Multi-Dimensional Ethical AI Adoption Model (MEAAM) / 2505.02062 / ISBN:https://doi.org/10.9734/ajmah/2025/v23i51228 / Published by ArXiv / on (web) Publishing site
1. Introduction
2. Literature Review and Theoretical Mechanism


Formalising Human-in-the-Loop: Computational Reductions, Failure Modes, and Legal-Moral Responsibility / 2505.10426 / ISBN:https://doi.org/10.48550/arXiv.2505.10426 / Published by ArXiv / on (web) Publishing site
Introduction


From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery / 2505.13259 / ISBN:https://doi.org/10.48550/arXiv.2505.13259 / Published by ArXiv / on (web) Publishing site
1 Introduction
6 Challenges and Future Directions


Aligning Trustworthy AI with Democracy: A Dual Taxonomy of Opportunities and Risks / 2505.13565 / ISBN:https://doi.org/10.48550/arXiv.2505.13565 / Published by ArXiv / on (web) Publishing site
7 Conclusion


AI vs. Human Judgment of Content Moderation: LLM-as-a-Judge and Ethics-Based Response Refusals / 2505.15365 / ISBN:https://doi.org/10.48550/arXiv.2505.15365 / Published by ArXiv / on (web) Publishing site
3 Methodology


Advancing the Scientific Method with Large Language Models: From Hypothesis to Discovery / 2505.16477 / ISBN:https://doi.org/10.48550/arXiv.2505.16477 / Published by ArXiv / on (web) Publishing site
Challenges and Opportunities
Conclusions


AI Literacy for Legal AI Systems: A practical approach / 2505.18006 / ISBN:https://doi.org/10.48550/arXiv.2505.18006 / Published by ArXiv / on (web) Publishing site
4. Legal AI Systems Benefit Assessment
5. Legal AI Systems Risk Assessment


Opacity as a Feature, Not a Flaw: The LoBOX Governance Ethic for Role-Sensitive Explainability and Institutional Trust in AI / 2505.20304 / ISBN:https://doi.org/10.48550/arXiv.2505.20304 / Published by ArXiv / on (web) Publishing site
1 Introduction
2 Opacity as a Frontier of Ethical Design
3 Operationalizing Ethical Governance: The Three-Stage LoBOX Framework Pathway for Managing Opacity
4 Application scenarios


Making Sense of the Unsensible: Reflection, Survey, and Challenges for XAI in Large Language Models Toward Human-Centered AI / 2505.20305 / ISBN:https://doi.org/10.48550/arXiv.2505.20305 / Published by ArXiv / on (web) Publishing site
Abstract
1 Introduction
2 Beyond Transparency: Why Explainability Is Essential for LLMs?
3 What Is XAI in the Context of LLMs?
5 Audience-Centered XAI role in LLMs
6 Mechanistic Interpretability: From Circuits to Cognitive Tracing in LLMs
7 Designing Actionable and Governable XAI: Challenges and Research Frontiers
8 Conclusion and Reflections


Simulating Ethics: Using LLM Debate Panels to Model Deliberation on Medical Dilemmas / 2505.21112 / ISBN:https://doi.org/10.48550/arXiv.2505.21112 / Published by ArXiv / on (web) Publishing site
5. Discussion


Human-Centered Human-AI Collaboration (HCHAC) / 2505.22477 / ISBN:https://doi.org/10.48550/arXiv.2505.22477 / Published by ArXiv / on (web) Publishing site
4. Current Research Agenda of HAC


Toward Effective AI Governance: A Review of Principles / 2505.23417 / ISBN:https://doi.org/10.48550/arXiv.2505.23417 / Published by ArXiv / on (web) Publishing site
III Results


Bottom-Up Perspectives on AI Governance: Insights from User Reviews of AI Products / 2506.00080 / ISBN:https://doi.org/10.48550/arXiv.2506.00080 / Published by ArXiv / on (web) Publishing site
4. Results


Ethical AI: Towards Defining a Collective Evaluation Framework / 2506.00233 / ISBN:https://doi.org/10.48550/arXiv.2506.00233 / Published by ArXiv / on (web) Publishing site
II Background


Wide Reflective Equilibrium in LLM Alignment: Bridging Moral Epistemology and AI Safety / 2506.00415 / ISBN:https://doi.org/10.48550/arXiv.2506.00415 / Published by ArXiv / on (web) Publishing site
Abstract
4. The Landscape of LLM Alignment: Methods and Challenges
5. Wide Reflective Equilibrium as the Descriptive Key to LLM Alignment
6. Normativity and the Limits of the Analogy
8. Future Research Directions and Broader Implications
9. Conclusion: Towards More Justified and Coherent AI Alignment


DeepSeek in Healthcare: A Survey of Capabilities, Risks, and Clinical Applications of Open-Source Large Language Models / 2506.01257 / ISBN:https://doi.org/10.48550/arXiv.2506.01257 / Published by ArXiv / on (web) Publishing site
Abstract
Training and Architecture
Comparisons with Other Models


Explainability in Context: A Multilevel Framework Aligning AI Explanations with Stakeholder with LLMs / 2506.05887 / ISBN:https://doi.org/10.48550/arXiv.2506.05887 / Published by ArXiv / on (web) Publishing site
1 Introduction
2 Background on Explainable AI and Audience-Centered Explanations
3 A Multilevel Framework for Audience-Aware Explainability