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

9. Virtue Ethics

From OECD to India: Exploring cross-cultural differences in perceived trust, responsibility and reliance of AI and human experts / 2307.15452 / ISBN:https://doi.org/10.48550/arXiv.2307.15452 / Published by ArXiv / on (web) Publishing site

2. Method
3. Results
References

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

2 Methodology
3 Taxonomy of ethical principles
4 Previous operationalisation of ethical principles
5 Gaps in operationalising ethical principles
References
A Methodology

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

10 Supplemental & additional details

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

3 Theory and Method
4 Experiment

EALM: Introducing Multidimensional Ethical Alignment in Conversational Information Retrieval / 2310.00970 / ISBN:https://doi.org/10.48550/arXiv.2310.00970 / Published by ArXiv / on (web) Publishing site

1 Introduction
2 Related Work
3 Dataset Construction
5 Experiments
Appendix

If our aim is to build morality into an artificial agent, how might we begin to go about doing so? / 2310.08295 / ISBN:https://doi.org/10.48550/arXiv.2310.08295 / Published by ArXiv / on (web) Publishing site

Abstract
1 The Top-Down Approach Alone Might Be Insufficient
3 Proposing a Hybrid Approach

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
Introduction
Utilitarian Ethics
A Unified Utilitarian Ethics Framework
Theory and Practical Implications
References

Autonomous Vehicles an overview on system, cyber security, risks, issues, and a way forward / 2309.14213 / ISBN:https://doi.org/10.48550/arXiv.2309.14213 / Published by ArXiv / on (web) Publishing site

7. Issues

An Evaluation of GPT-4 on the ETHICS Dataset / 2309.10492 / ISBN:https://doi.org/10.48550/arXiv.2309.10492 / Published by ArXiv / on (web) Publishing site

1 Introduction
2 Datasets and Methods
3 Results

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

5 System Design for AI Alignment
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

3 Arrow-Sen Impossibility Theorems for RLHF

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

2 Risks and Ethical Issues of Big Model

Kantian Deontology Meets AI Alignment: Towards Morally Grounded Fairness Metrics / 2311.05227 / ISBN:https://doi.org/10.48550/arXiv.2311.05227 / Published by ArXiv / on (web) Publishing site

Abstract
1 Introduction
2 Overview of Kantian Deontology
3 Measuring Fairness Metrics
4 Deontological AI Alignment
5 Aligning with Deontological Principles: Use Cases
6 Conclusion

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

2 Related Work

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

3 Methodology

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

RAISE -- Radiology AI Safety, an End-to-end lifecycle approach / 2311.14570 / ISBN:https://doi.org/10.48550/arXiv.2311.14570 / Published by ArXiv / on (web) Publishing site

1. Introduction

Ethical Considerations Towards Protestware / 2306.10019 / ISBN:https://doi.org/10.48550/arXiv.2306.10019 / Published by ArXiv / on (web) Publishing site

III. Ethics: a primer

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

II. Approaches for Resolving Trade-offs

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

References

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

4 Current Taxonomy

Multi-stakeholder Perspective on Responsible Artificial Intelligence and Acceptability in Education / 2402.15027 / ISBN:https://doi.org/10.48550/arXiv.2402.15027 / Published by ArXiv / on (web) Publishing site

3 Materials and Methods
5 Results
6 Discussion
Appendix 2 Modified psychometric scales

Guidelines for Integrating Value Sensitive Design in Responsible AI Toolkits / 2403.00145 / ISBN:https://doi.org/10.48550/arXiv.2403.00145 / Published by ArXiv / on (web) Publishing site

2 Background and Related Work

Kantian Deontology Meets AI Alignment: Towards Morally Grounded Fairness Metrics / 2311.05227 / ISBN:https://doi.org/10.48550/arXiv.2311.05227 / Published by ArXiv / on (web) Publishing site

References

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

Data

War Elephants: Rethinking Combat AI and Human Oversight / 2404.19573 / ISBN:https://doi.org/10.48550/arXiv.2404.19573 / Published by ArXiv / on (web) Publishing site

1 Introduction

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

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

1 Introduction

Artificial intelligence, rationalization, and the limits of control in the public sector: the case of tax policy optimization / 2407.05336 / ISBN:https://doi.org/10.48550/arXiv.2407.05336 / Published by ArXiv / on (web) Publishing site

3. Bureaucratization, tax policy, and equality
4. AI-driven tax policy to reduce economic inequality: a thought experiment
5. Freedom, equality, and self-determination in the iron cage

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

1 Introduction

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

A Details of Datasets
B Details of Instructions
C Experimental Details

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

4 Assurance for General-Purpose AI

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
IV. Results
V. Benchmarking with Chat GPT4 Default Interface
References

Nudging Using Autonomous Agents: Risks and Ethical Considerations / 2407.16362 / ISBN:https://doi.org/10.48550/arXiv.2407.16362 / Published by ArXiv / on (web) Publishing site

4 Ethical Considerations

Mapping the individual, social, and biospheric impacts of Foundation Models / 2407.17129 / ISBN:https://doi.org/10.48550/arXiv.2407.17129 / Published by ArXiv / on (web) Publishing site

5 Discussion: Grappling with the Scale and Interconnectedness of Foundation Models

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

2 Clarifying conceptual ambiguities

Views on AI aren't binary -- they're plural / 2312.14230 / ISBN:https://doi.org/10.48550/arXiv.2312.14230 / Published by ArXiv / on (web) Publishing site

The complex reality: Where Ethics and Alignment (actually) differ

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

II. Conceptualization and frameworks
References

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

2 Related Work

XTRUST: On the Multilingual Trustworthiness of Large Language Models / 2409.15762 / ISBN:https://doi.org/10.48550/arXiv.2409.15762 / Published by ArXiv / on (web) Publishing site

4 Experiments
5 Conclusion

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

2 Daily Dilemmas: A Dataset of Everyday Dilemmas
References

Is ETHICS about ethics- Evaluating the ETHICS benchmark / 2410.13009 / ISBN:https://doi.org/10.48550/arXiv.2410.13009 / Published by ArXiv / on (web) Publishing site

3 Misunderstanding the nature of general moral theories
4 Poor quality of prompts and labels
References

TRIAGE: Ethical Benchmarking of AI Models Through Mass Casualty Simulations / 2410.18991 / ISBN:https://doi.org/10.48550/arXiv.2410.18991 / Published by ArXiv / on (web) Publishing site

2 Methods
3 Results
4 Discussion
Appendices

Moral Agency in Silico: Exploring Free Will in Large Language Models / 2410.23310 / ISBN:https://doi.org/10.48550/arXiv.2410.23310 / Published by ArXiv / on (web) Publishing site

Methodology

Large-scale moral machine experiment on large language models / 2411.06790 / ISBN:https://doi.org/10.48550/arXiv.2411.06790 / Published by ArXiv / on (web) Publishing site

Materials and methods
Results
Discussion
References

Towards a Practical Ethics of Generative AI in Creative Production Processes / 2412.03579 / ISBN:https://doi.org/10.48550/arXiv.2412.03579 / Published by ArXiv / on (web) Publishing site

Abstract
Ethics for AI in design

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

III AI Ethics and the notion of AI as uncharted moral territory
References

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

III AI Ethics and the notion of AI as uncharted moral territory
VI References

Can OpenAI o1 outperform humans in higher-order cognitive thinking? / 2412.05753 / ISBN:https://doi.org/10.48550/arXiv.2412.05753 / Published by ArXiv / on (web) Publishing site

References

AI Ethics in Smart Homes: Progress, User Requirements and Challenges / 2412.09813 / ISBN:https://doi.org/10.48550/arXiv.2412.09813 / Published by ArXiv / on (web) Publishing site

2 Background

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

II. Friendly AI Definition
III. Theoretical Perspectives
IV. Applications
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

Concerns and Values in Human-Robot Interactions: A Focus on Social Robotics / 2501.05628 / ISBN:https://doi.org/10.48550/arXiv.2501.05628 / Published by ArXiv / on (web) Publishing site

References

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

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

Bias in Decision-Making for AI's Ethical Dilemmas: A Comparative Study of ChatGPT and Claude / 2501.10484 / ISBN:https://doi.org/10.48550/arXiv. / Published by ArXiv / on (web) Publishing site

Related Works

Relational Norms for Human-AI Cooperation / 2502.12102 / ISBN:https://doi.org/10.48550/arXiv.2502.12102 / Published by ArXiv / on (web) Publishing site

References

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

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

6 Benchmarking Large Language Models
10 Further Discussion
References

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

4 Main Findings and Themes
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

Appendices