Why_this_webapp Bibliography

A multilevel framework for AI governance / 2307.03198 / ISBN:https://doi.org/10.48550/arXiv.2307.03198 / Published by ArXiv / on (web) Publishing site

6. Psychology of Trust

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

Who to Trust, How and Why: Untangling AI Ethics Principles, Trustworthiness and Trust / 2309.10318 / ISBN:https://doi.org/10.48550/arXiv.2309.10318 / Published by ArXiv / on (web) Publishing site

Trust

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

Contents
1 Introduction
2 AI feedback on specific problematic AI traits
4 Reinforcement Learning with Good-for-Humanity Preference Models
5 Related Work
7 Contribution Statement
A Model Glossary

The Self 2.0: How AI-Enhanced Self-Clones Transform Self-Perception and Improve Presentation Skills / 2310.15112 / ISBN:https://doi.org/10.48550/arXiv.2310.15112 / Published by ArXiv / on (web) Publishing site

2 Related Work
4 Findings
5 Discussion

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

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

4 Equilibrium Alignment: A Prospective Paradigm for Ethical Value Alignmen

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

Unlocking the Potential of ChatGPT: A Comprehensive Exploration of its Applications, Advantages, Limitations, and Future Directions in Natural Language Processing / 2304.02017 / ISBN:https://doi.org/10.48550/arXiv.2304.02017 / Published by ArXiv / on (web) Publishing site

4 Applications of ChatGPT in real-world scenarios

Synergizing Human-AI Agency: A Guide of 23 Heuristics for Service Co-Creation with LLM-Based Agents / 2310.15065 / ISBN:https://doi.org/10.48550/arXiv.2310.15065 / Published by ArXiv / on (web) Publishing site

4 Findings

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

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

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

1 Introduction
2 UnknownBench: Evaluating LLMs on the Unknown
3 Experiments

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

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

1 Introduction
3 Control the Risks of AI Models in Science
Appendix D Details of Benchmark Results

The AI Assessment Scale (AIAS): A Framework for Ethical Integration of Generative AI in Educational Assessment / 2312.07086 / ISBN:https://doi.org/10.48550/arXiv.2312.07086 / Published by ArXiv / on (web) Publishing site

The AI Assessment Scale

Improving Task Instructions for Data Annotators: How Clear Rules and Higher Pay Increase Performance in Data Annotation in the AI Economy / 2312.14565 / ISBN:https://doi.org/10.48550/arXiv.2312.14565 / Published by ArXiv / on (web) Publishing site

II. Theoretical background and hypotheses
III. Method
IV. Results
V. 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

4 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

AI Alignment: A Comprehensive Survey / 2310.19852 / ISBN:https://doi.org/10.48550/arXiv.2310.19852 / Published by ArXiv / on (web) Publishing site

2 Learning from Feedback
4 Assurance
5 Governance

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

9 The Enduring Irresponsibility of AI Rights Talk

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

4 LLM Lifecycle

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

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
Figures and tables

Documenting Ethical Considerations in Open Source AI Models / 2406.18071 / ISBN:https://doi.org/10.48550/arXiv.2406.18071 / Published by ArXiv / on (web) Publishing site

2 RELATED WORK

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

Interactive embodied evolution for socially adept Artificial General Creatures / 2407.21357 / ISBN:https://doi.org/10.48550/arXiv.2407.21357 / Published by ArXiv / on (web) Publishing site

Introduction

Exploring the Role of Social Support when Integrating Generative AI into Small Business Workflows / 2407.21404 / ISBN:https://doi.org/10.48550/arXiv.2407.21404 / Published by ArXiv / on (web) Publishing site

4 Findings

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

3. Proposed framework

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

2 Methodology & Guidelines
3 Data Sources

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

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

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

4 Operationalizing ValueCompass: Methods to Measure Value Alignment of Humans and AI
5 Findings with ValueCompass: The Status Quo of Human-AI Value Alignment
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
5 User Study Methodology
6 User Study Results
A Appendix

Ethical software requirements from user reviews: A systematic literature review / 2410.01833 / ISBN:https://doi.org/10.48550/arXiv.2410.01833 / Published by ArXiv / on (web) Publishing site

IV. Results

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

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

Study on the Helpfulness of Explainable Artificial Intelligence / 2410.11896 / ISBN:https://doi.org/10.48550/arXiv.2410.11896 / Published by ArXiv / on (web) Publishing site

Abstract
1 Introduction
2 Measuring Explainability
Appendix B Demographic overview of participants

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

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

The Dark Side of AI Companionship: A Taxonomy of Harmful Algorithmic Behaviors in Human-AI Relationships / 2410.20130 / ISBN:https://doi.org/10.48550/arXiv.2410.20130 / Published by ArXiv / on (web) Publishing site

5 Discussion

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

Nteasee: A mixed methods study of expert and general population perspectives on deploying AI for health in African countries / 2409.12197 / ISBN:https://doi.org/10.48550/arXiv.2409.12197 / Published by ArXiv / on (web) Publishing site

3 Results

Towards Friendly AI: A Comprehensive Review and New Perspectives on Human-AI Alignment / 2412.15114 / ISBN:https://doi.org/10.48550/arXiv.2412.15114 / Published by ArXiv / on (web) Publishing site

III. Theoretical Perspectives

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

Towards Safe AI Clinicians: A Comprehensive Study on Large Language Model Jailbreaking in Healthcare / 2501.18632 / ISBN:https://doi.org/10.48550/arXiv. / Published by ArXiv / on (web) Publishing site

Introduction
Jailbreak Evaluation Method

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

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
References
Appendices

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

1 Introduction
3 Guidelines of Trustworthy Generative Foundation Models
6 Benchmarking Large Language Models
9 Trustworthiness in Downstream Applications
10 Further Discussion
References