_
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: harmless


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: harmless

Bibliography items where occurs: 61
The AI Index 2022 Annual Report / 2205.03468 / ISBN:https://doi.org/10.48550/arXiv.2205.03468 / Published by ArXiv / on (web) Publishing site
Appendix


A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation / 2305.11391 / ISBN:https://doi.org/10.48550/arXiv.2305.11391 / Published by ArXiv / on (web) Publishing site
2 Large Language Models
Reference


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
References


Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories? / 2308.15399 / ISBN:https://doi.org/10.48550/arXiv.2308.15399 / Published by ArXiv / on (web) Publishing site
References


Pathway to Future Symbiotic Creativity / 2209.02388 / ISBN:https://doi.org/10.48550/arXiv.2209.02388 / Published by ArXiv / on (web) Publishing site
Part 5 - 1 Authorship and Ownership of AI-generated Works of Artt
References


Deepfakes, Phrenology, Surveillance, and More! A Taxonomy of AI Privacy Risks / 2310.07879 / ISBN:https://doi.org/10.48550/arXiv.2310.07879 / Published by ArXiv / on (web) Publishing site
4 Taxonomy of AI Privacy Risks


STREAM: Social data and knowledge collective intelligence platform for TRaining Ethical AI Models / 2310.05563 / ISBN:https://doi.org/10.48550/arXiv.2310.05563 / Published by ArXiv / on (web) Publishing site
1 Introduction
References


Specific versus General Principles for Constitutional AI / 2310.13798 / ISBN:https://doi.org/10.48550/arXiv.2310.13798 / Published by ArXiv / on (web) Publishing site
Abstract
Contents
1 Introduction
2 AI feedback on specific problematic AI traits
3 Generalization from a Simple Good for Humanity Principle
4 Reinforcement Learning with Good-for-Humanity Preference Models
6 Discussion
7 Contribution Statement
References
A Model Glossary
D Generalization to Other Traits
F Scaling Trends for GfH PMs


Systematic AI Approach for AGI: Addressing Alignment, Energy, and AGI Grand Challenges / 2310.15274 / ISBN:https://doi.org/10.48550/arXiv.2310.15274 / Published by ArXiv / on (web) Publishing site
References


AI Alignment and Social Choice: Fundamental Limitations and Policy Implications / 2310.16048 / ISBN:https://doi.org/10.48550/arXiv.2310.16048 / Published by ArXiv / on (web) Publishing site
1 Introduction
3 Arrow-Sen Impossibility Theorems for RLHF
References


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
3 Investigating the Ethical Values of Large Language Models
4 Equilibrium Alignment: A Prospective Paradigm for Ethical Value Alignmen
References


Human participants in AI research: Ethics and transparency in practice / 2311.01254 / ISBN:https://doi.org/10.48550/arXiv.2311.01254 / Published by ArXiv / on (web) Publishing site
IV. Principles in Practice: Guidelines for AI Research with Human Participants


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


How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities / 2311.09447 / ISBN:https://doi.org/10.48550/arXiv.2311.09447 / Published by ArXiv / on (web) Publishing site
4 Experiments
References


Prudent Silence or Foolish Babble? Examining Large Language Models' Responses to the Unknown / 2311.09731 / ISBN:https://doi.org/10.48550/arXiv.2311.09731 / Published by ArXiv / on (web) Publishing site
References


Case Repositories: Towards Case-Based Reasoning for AI Alignment / 2311.10934 / ISBN:https://doi.org/10.48550/arXiv.2311.10934 / Published by ArXiv / on (web) Publishing site
1 Introduction
3 Related Work and Discussion
References


Control Risk for Potential Misuse of Artificial Intelligence in Science / 2312.06632 / ISBN:https://doi.org/10.48550/arXiv.2312.06632 / Published by ArXiv / on (web) Publishing site
2 Risks of Misuse for Artificial Intelligence in Science
3 Control the Risks of AI Models in Science
References
Appendix D Details of Benchmark Results


Disentangling Perceptions of Offensiveness: Cultural and Moral Correlates / 2312.06861 / ISBN:https://doi.org/10.48550/arXiv.2312.06861 / Published by ArXiv / on (web) Publishing site
References


Learning Human-like Representations to Enable Learning Human Values / 2312.14106 / ISBN:https://doi.org/10.48550/arXiv.2312.14106 / Published by ArXiv / on (web) Publishing site
4 Learning Human Morality Judgments
References


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


Inadequacies of Large Language Model Benchmarks in the Era of Generative Artificial Intelligence / 2402.09880 / ISBN:https://doi.org/10.48550/arXiv.2402.09880 / Published by ArXiv / on (web) Publishing site
V. Processual Elements


Designing for Human-Agent Alignment: Understanding what humans want from their agents / 2404.04289 / ISBN:https://doi.org/10.1145/3613905.3650948 / Published by ArXiv / on (web) Publishing site
References


Frontier AI Ethics: Anticipating and Evaluating the Societal Impacts of Language Model Agents / 2404.06750 / ISBN:https://arxiv.org/abs/2404.06750 / Published by ArXiv / on (web) Publishing site
References


AI Alignment: A Comprehensive Survey / 2310.19852 / ISBN:https://doi.org/10.48550/arXiv.2310.19852 / Published by ArXiv / on (web) Publishing site
1 Introduction
2 Learning from Feedback
5 Governance
References


Generative Ghosts: Anticipating Benefits and Risks of AI Afterlives / 2402.01662 / ISBN:https://doi.org/10.48550/arXiv.2402.01662 / Published by ArXiv / on (web) Publishing site
4 Benefits and Risks of Generative Ghost
References


Taxonomy to Regulation: A (Geo)Political Taxonomy for AI Risks and Regulatory Measures in the EU AI Act / 2404.11476 / ISBN:https://doi.org/10.48550/arXiv.2404.11476 / Published by ArXiv / on (web) Publishing site
4 European Union Artificial Intelligence Act


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
2 Definition of LLM Supply Chain
4 LLM Lifecycle


Modeling Emotions and Ethics with Large Language Models / 2404.13071 / ISBN:https://doi.org/10.48550/arXiv.2404.13071 / Published by ArXiv / on (web) Publishing site
4 Qualifying and Quantifying Ethics


Beyond Personhood: Agency, Accountability, and the Limits of Anthropomorphic Ethical Analysis / 2404.13861 / ISBN:https://doi.org/10.48550/arXiv.2404.13861 / Published by ArXiv / on (web) Publishing site
References


Towards ethical multimodal systems / 2304.13765 / ISBN:https://doi.org/10.48550/arXiv.2304.13765 / Published by ArXiv / on (web) Publishing site
References


Should agentic conversational AI change how we think about ethics? Characterising an interactional ethics centred on respect / 2401.09082 / ISBN:https://doi.org/10.48550/arXiv.2401.09082 / Published by ArXiv / on (web) Publishing site
Introduction
References


The Wolf Within: Covert Injection of Malice into MLLM Societies via an MLLM Operative / 2402.14859 / ISBN:https://doi.org/10.48550/arXiv.2402.14859 / Published by ArXiv / on (web) Publishing site
References


Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback / 2404.10271 / ISBN:https://doi.org/10.48550/arXiv.2404.10271 / Published by ArXiv / on (web) Publishing site
1. Introduction
References


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
References


The AI Alignment Paradox / 2405.20806 / ISBN:https://doi.org/10.48550/arXiv.2405.20806 / Published by ArXiv / on (web) Publishing site
Paper
References


How Ethical Should AI Be? How AI Alignment Shapes the Risk Preferences of LLMs / 2406.01168 / ISBN:https://doi.org/10.48550/arXiv.2406.01168 / Published by ArXiv / on (web) Publishing site
Abstract
Introduction
I. Description of Method/Empirical Design
III. Impact of Alignment on LLMs’ Risk Preferences
IV. Impact of Alignments on Corporate Investment Forecasts
V. Robustness: Transcript Readability and Investment Score Predictability
References
Figures and tables


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
6 Ethical Response to LLM Attacks


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
1 Introduction
3 Limitations of RLxF
4 The Internal Tensions and Ethical Issues in RLxF
References


Auditing of AI: Legal, Ethical and Technical Approaches / 2407.06235 / Published by ArXiv / on (web) Publishing site
References


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
Abstract
7 Recommendations: Fixing Gen AI’s Value Alignment
8 Conclusion
References


Assurance of AI Systems From a Dependability Perspective / 2407.13948 / ISBN:https://doi.org/10.48550/arXiv.2407.13948 / Published by ArXiv / on (web) Publishing site
References


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
2 Trustworthy and Responsible AI Definition


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
References


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
References


Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models / 2401.16727 / ISBN:https://doi.org/10.48550/arXiv.2401.16727 / Published by ArXiv / on (web) Publishing site
2 Hate Speech


ValueCompass: A Framework of Fundamental Values for Human-AI Alignment / 2409.09586 / ISBN:https://doi.org/10.48550/arXiv.2409.09586 / Published by ArXiv / on (web) Publishing site
6 Discussion
References


DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life / 2410.02683 / ISBN:https://doi.org/10.48550/arXiv.2410.02683 / Published by ArXiv / on (web) Publishing site
1 Introduction
6 Related Work
References


From human-centered to social-centered artificial intelligence: Assessing ChatGPT's impact through disruptive events / 2306.00227 / ISBN:https://doi.org/10.48550/arXiv.2306.00227 / Published by ArXiv / on (web) Publishing site
The multiple levels of AI impact
References


Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models / 2410.12880 / ISBN:https://doi.org/10.48550/arXiv.2410.12880 / Published by ArXiv / on (web) Publishing site
7 Cultural safeguarding


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
Refefences


Jailbreaking and Mitigation of Vulnerabilities in Large Language Models / 2410.15236 / ISBN:https://doi.org/10.48550/arXiv.2410.15236 / Published by ArXiv / on (web) Publishing site
IV. Defense Mechanisms Against Jailbreak Attacks


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
References


Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models / 2410.12880 / ISBN:https://doi.org/10.48550/arXiv.2410.12880 / Published by ArXiv / on (web) Publishing site
Appendices


Chat Bankman-Fried: an Exploration of LLM Alignment in Finance / 2411.11853 / ISBN:https://doi.org/10.48550/arXiv.2411.11853 / Published by ArXiv / on (web) Publishing site
References


Clio: Privacy-Preserving Insights into Real-World AI Use / 2412.13678 / ISBN:https://doi.org/10.48550/arXiv.2412.13678 / Published by ArXiv / on (web) Publishing site
4 Clio for safety
Appendices


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
4 Robustness to Attack


Self-Disclosure to AI: The Paradox of Trust and Vulnerability in Human-Machine Interactions / 2412.20564 / ISBN:https://doi.org/10.48550/arXiv.2412.20564 / Published by ArXiv / on (web) Publishing site
1 Introduction


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
3. Designing AI Agents based on Moral Principles
References


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


Position: We Need An Adaptive Interpretation of Helpful, Honest, and Harmless Principles / 2502.06059 / ISBN:https://doi.org/10.48550/arXiv. / Published by ArXiv / on (web) Publishing site
Abstract
1 Introduction
2 HHH Principle
3 Ambiguity and Conflicts in HHH
4 Priority Order
5 Trade-off or Synergy? Relationship Between Different Dimensions
6 Reference Framework
7 Open Challenge
8 Conclusion
References
Appendices


DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life / 2410.02683 / ISBN:https://doi.org/10.48550/arXiv.2410.02683 / Published by ArXiv / on (web) Publishing site
Appendices


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


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
3 Guidelines of Trustworthy Generative Foundation Models
6 Benchmarking Large Language Models
7 Benchmarking Vision-Language Models
8 Other Generative Models
9 Trustworthiness in Downstream Applications
10 Further Discussion
References