Why_this_webapp Bibliography

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

1 Introduction
2 Large Language Models
5 Falsification and Evaluation
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

I. Introduction
II. Methods and training process of LLMs
VI. Solution architecture for privacy-aware and trustworthy conversational AI

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

4 Experiment

The Impact of Artificial Intelligence on the Evolution of Digital Education: A Comparative Study of OpenAI Text Generation Tools including ChatGPT, Bing Chat, Bard, and Ernie / 2309.02029 / ISBN:https://doi.org/10.48550/arXiv.2309.02029 / Published by ArXiv / on (web) Publishing site

5. Discussion

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

3. From PLMs to LLMs for healthcare
5. Improving fairness, accountability, transparency, and ethics

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

3 The applications of STREAM

Regulation and NLP (RegNLP): Taming Large Language Models / 2310.05553 / ISBN:https://doi.org/10.48550/arXiv.2310.05553 / Published by ArXiv / on (web) Publishing site

3 LLMs: Risk and Uncertainty

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

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
5 Related Work
6 Discussion
A Model Glossary
D Generalization to Other Traits
G Over-Training on Good for Humanity
H Samples
I Responses on Prompts from PALMS, LaMDA, and InstructGPT

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

Abstract
1 Introduction
2 Reinforcement Learning with Multiple Reinforcers
3 Arrow-Sen Impossibility Theorems for RLHF
4 Implications for AI Governance and Policy
5 Conclusion

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
2 Risks and Ethical Issues of Big Model
3 Investigating the Ethical Values of Large Language Models
4 Equilibrium Alignment: A Prospective Paradigm for Ethical Value Alignmen

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

4 The Moral Model
A Supplementary Material

She had Cobalt Blue Eyes: Prompt Testing to Create Aligned and Sustainable Language Models / 2310.18333 / ISBN:https://doi.org/10.48550/arXiv.2310.18333 / Published by ArXiv / on (web) Publishing site

2 Related Works
4 Empirical Evaluation and Outcomes

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

1 Introduction
4 Experiments

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

Abstract
1 Introduction
2 UnknownBench: Evaluating LLMs on the Unknown
3 Experiments
5 Conclusion
D Additional Results and Figures

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

3 Related Work and Discussion

Potential Societal Biases of ChatGPT in Higher Education: A Scoping Review / 2311.14381 / ISBN:https://doi.org/10.48550/arXiv.2311.14381 / Published by ArXiv / on (web) Publishing site

OVERVIEW OF SOCIETAL BIASES IN GAI MODELS

Generative AI and US Intellectual Property Law / 2311.16023 / ISBN:https://doi.org/10.48550/arXiv.2311.16023 / Published by ArXiv / on (web) Publishing site

V. Potential harms and mitigation

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

1 Introduction

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

1 The “Triple-Too” problem of AI ethics
3 Five specific goals and action-guiding strategies for ethical AI use in research practices

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

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

Evaluation Ethics of LLMs in Legal Domain / 2403.11152 / ISBN:https://doi.org/10.48550/arXiv.2403.11152 / Published by ArXiv / on (web) Publishing site

4 Experiment

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

5 Ways to mitigate bias and promote Fairness

A Review of Multi-Modal Large Language and Vision Models / 2404.01322 / ISBN:https://doi.org/10.48550/arXiv.2404.01322 / Published by ArXiv / on (web) Publishing site

1 Introduction
4 Specific Large Language Models
6 Model Tuning
8 Conclusions
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

A Primer
Rebooting Machine Ethics
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
4 Assurance
5 Governance
6 Conclusion
References

Debunking Robot Rights Metaphysically, Ethically, and Legally / 2404.10072 / ISBN:https://doi.org/10.48550/arXiv.2404.10072 / Published by ArXiv / on (web) Publishing site

3 The Robots at Issue

The Necessity of AI Audit Standards Boards / 2404.13060 / ISBN:https://doi.org/10.48550/arXiv.2404.13060 / Published by ArXiv / on (web) Publishing site

2 Audit the process, not just the product

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

2 Mechanistic Agency: A Common View in AI Practice
4 Alternatives to AI as Agent
References

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

6 Ethics

Organizing a Society of Language Models: Structures and Mechanisms for Enhanced Collective Intelligence / 2405.03825 / ISBN:https://doi.org/10.48550/arXiv.2405.03825 / Published by ArXiv / on (web) Publishing site

2 Motivation

XXAI: Towards eXplicitly eXplainable Artificial Intelligence / 2401.03093 / ISBN:https://doi.org/10.48550/arXiv.2401.03093 / 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
2. Background
3. What Are the Collective Decision Problems and their Alternatives in this Context?
4. Who Provides the Human Feedback?
5. What Is the Format of Human Feedback?
6. How Do We Incorporate Diverse Individual Feedback?
7. Which Traditional Social-Choice-Theoretic Concepts Are Most Relevant?
10. Conclusion
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

1 Introduction
2 Related Work
3 Quantitative Models of Emotions, Behaviors, and Ethics

When AI Eats Itself: On the Caveats of Data Pollution in the Era of Generative AI / 2405.09597 / ISBN:https://doi.org/10.48550/arXiv.2405.09597 / Published by ArXiv / on (web) Publishing site

3 RQ2: What Technical Strategies Can Be Employed to Mitigate the Negative Consequences of AI Autophagy?

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

III. Impact of Alignment on LLMs’ Risk Preferences
Figures and tables

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

References
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

3 Strategies in Securing Large Language models

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

II. RECENT ADVANCEMENTS IN LARGE LANGUAGE MODELS

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
2 Background
3 Limitations of RLxF
4 The Internal Tensions and Ethical Issues in RLxF
5 Rebooting Safety and Alignment: Integrating AI Ethics and System Safety
References

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

RogueGPT: dis-ethical tuning transforms ChatGPT4 into a Rogue AI in 158 Words / 2407.15009 / ISBN:https://doi.org/10.48550/arXiv.2407.15009 / Published by ArXiv / on (web) Publishing site

II. Background
III. Methodology

The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources / 2406.16746 / ISBN:https://doi.org/10.48550/arXiv.2406.16746 / Published by ArXiv / on (web) Publishing site

8 Model Evaluation

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

IV. Challenges of Generative AI and LLMs

Don't Kill the Baby: The Case for AI in Arbitration / 2408.11608 / ISBN:https://doi.org/10.48550/arXiv.2408.11608 / Published by ArXiv / on (web) Publishing site

I. AI and the Federal Arbitration ACt

CIPHER: Cybersecurity Intelligent Penetration-testing Helper for Ethical Researcher / 2408.11650 / ISBN:https://doi.org/10.48550/arXiv.2408.11650 / Published by ArXiv / on (web) Publishing site

2. Background and Related Works

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

4 Adapting General LLMs to the Biomedical Field

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

4. Risks and Caveats
5. Annoyances or Dealbreakers?

On the Creativity of Large Language Models / 2304.00008 / ISBN:https://doi.org/10.48550/arXiv.2304.00008 / Published by ArXiv / on (web) Publishing site

2 A Creative Journey from Ada Lovelace to Foundation Models
3 Large Language Models and Boden’s Three Criteria
References

Data-Centric Foundation Models in Computational Healthcare: A Survey / 2401.02458 / ISBN:https://doi.org/10.48550/arXiv.2401.02458 / Published by ArXiv / on (web) Publishing site

8 Performance Evaluation

Large language models as linguistic simulators and cognitive models in human research / 2402.04470 / ISBN:https://doi.org/10.48550/arXiv.2402.04470 / Published by ArXiv / on (web) Publishing site

Language models as human participants
Six fallacies that misinterpret language models
Using language models to simulate roles and model cognitive processes

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

GenAI Advertising: Risks of Personalizing Ads with LLMs / 2409.15436 / ISBN:https://doi.org/10.48550/arXiv.2409.15436 / Published by ArXiv / on (web) Publishing site

2 Background and Related Work

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

6 Related Work

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

1 Introduction

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

2 Background and Related Works

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

II. Background and Concepts
VI. Research Gaps and Future Directions
VII. Conclusion

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

1 Introduction
2 Background and Related Work
3 Interactive-Reflective Dialogue Alignment (IRDA) System
7 Discussion
References

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

II. Background and Technology
III. From General to Medical-Specific LLMs

Framework for developing and evaluating ethical collaboration between expert and machine / 2411.10983 / ISBN:https://doi.org/10.48550/arXiv.2411.10983 / Published by ArXiv / on (web) Publishing site

2. Method

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

2. Understanding Large Language Models

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

2 Preliminaries
References

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

3 Value Misalignment
8 Interpretability for LLM Safety
9 Technology Roadmaps / Strategies to LLM Safety in Practice

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
2. Learning Morality in Machines
3. Designing AI Agents based on Moral Principles
Definitions

Open Foundation Models in Healthcare: Challenges, Paradoxes, and Opportunities with GenAI Driven Personalized Prescription / 2502.04356 / ISBN:https://doi.org/10.48550/arXiv. / Published by ArXiv / on (web) Publishing site

III. State-of-the-Art in Open Healthcare LLMs and AIFMs
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

2 HHH Principle
References
Appendices

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

4 Language models in medicine
Additional information

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

4 Implications
References

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
9 Trustworthiness in Downstream Applications
10 Further Discussion
References

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

3. Results

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

5 Mitigation Strategies

A Systematic Decade Review of Trip Route Planning with Travel Time Estimation based on User Preferences and Behavior / 2503.23486 / ISBN:https://doi.org/10.48550/arXiv.2503.23486 / Published by ArXiv / on (web) Publishing site

References