{"total":291,"rows":[{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437,"area":null},{"id":"2302.07241","title":"ConceptFusion: Open-set Multimodal 3D Mapping","created":"2023-02-14","cited_by_count":304,"area":null},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258,"area":null},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168,"area":null},{"id":"2402.01364","title":"Continual Learning for Large Language Models: A Survey","created":"2024-02-02","cited_by_count":147,"area":null},{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143,"area":null},{"id":"2302.08500","title":"Auditing large language models: a three-layered approach","created":"2023-02-16","cited_by_count":137,"area":null},{"id":"2205.11275","title":"RL with KL penalties is better viewed as Bayesian inference","created":"2022-05-23","cited_by_count":135,"area":null},{"id":"2303.15715","title":"Foundation Models and Fair Use","created":"2023-03-28","cited_by_count":116,"area":null},{"id":"2203.07785","title":"The Ghost in the Machine has an American accent: value conflict in GPT-3","created":"2022-03-15","cited_by_count":105,"area":null},{"id":"2308.14840","title":"Identifying and Mitigating the Security Risks of Generative AI","created":"2023-08-28","cited_by_count":91,"area":null},{"id":"2305.09863","title":"Explaining black box text modules in natural language with language models","created":"2023-05-17","cited_by_count":62,"area":null},{"id":"2402.17385","title":"Determinants of LLM-assisted Decision-Making","created":"2024-02-27","cited_by_count":56,"area":null},{"id":"2204.13988","title":"A Taxonomy of Prompt Modifiers for Text-To-Image Generation","created":"2022-04-20","cited_by_count":55,"area":null},{"id":"2209.12226","title":"Re-contextualizing Fairness in NLP: The Case of India","created":"2022-09-25","cited_by_count":55,"area":null},{"id":"2504.15236","title":"Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions","created":"2025-04-21","cited_by_count":52,"area":null},{"id":"2501.15463","title":"Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?","created":"2025-01-26","cited_by_count":51,"area":null},{"id":"2311.10766","title":"Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values","created":"2023-11-15","cited_by_count":50,"area":null},{"id":"2107.13509","title":"The Who in XAI: How AI Background Shapes Perceptions of AI Explanations","created":"2021-07-28","cited_by_count":48,"area":null},{"id":"2502.02528","title":"Why human-AI relationships need socioaffective alignment","created":"2025-02-04","cited_by_count":47,"area":null},{"id":"2203.07475","title":"Invariance in Policy Optimisation and Partial Identifiability in Reward Learning","created":"2022-03-14","cited_by_count":46,"area":null},{"id":"2402.11905","title":"Learning to Edit: Aligning LLMs with Knowledge Editing","created":"2024-02-19","cited_by_count":43,"area":null},{"id":"2311.08993","title":"When does In-context Learning Fall Short and Why? A Study on Specification-Heavy Tasks","created":"2023-11-15","cited_by_count":37,"area":null},{"id":"2403.14680","title":"Trust in AI: Progress, Challenges, and Future Directions","created":"2024-03-12","cited_by_count":35,"area":null},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2502.12206","title":"Evaluating the Paperclip Maximizer: Are RL-Based Language Models More Likely to Pursue Instrumental Goals?","created":"2025-02-16","cited_by_count":33,"area":null},{"id":"2303.12642","title":"Democratising AI: Multiple Meanings, Goals, and Methods","created":"2023-03-22","cited_by_count":29,"area":null},{"id":"2405.20956","title":"A Robot Walks into a Bar: Can Language Models Serve as Creativity Support Tools for Comedy? An Evaluation of LLMs' Humour Alignment with Comedians","created":"2024-05-31","cited_by_count":29,"area":null},{"id":"2401.02458","title":"Data-Centric Foundation Models in Computational Healthcare: A Survey","created":"2024-01-04","cited_by_count":27,"area":null},{"id":"2401.02994","title":"Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM","created":"2024-01-04","cited_by_count":27,"area":null},{"id":"2310.11053","title":"Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning","created":"2023-10-17","cited_by_count":26,"area":null},{"id":"2312.06861","title":"Disentangling Perceptions of Offensiveness: Cultural and Moral Correlates","created":"2023-12-11","cited_by_count":26,"area":null},{"id":"2401.13986","title":"Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning","created":"2024-01-25","cited_by_count":26,"area":null},{"id":"2301.11990","title":"Alignment with human representations supports robust few-shot learning","created":"2023-01-27","cited_by_count":25,"area":null},{"id":"2401.14362","title":"The Typing Cure: Experiences with Large Language Model Chatbots for Mental Health Support","created":"2024-01-25","cited_by_count":24,"area":null},{"id":"2406.01382","title":"Do Large Language Models Perform the Way People Expect? Measuring the Human Generalization Function","created":"2024-06-03","cited_by_count":24,"area":null},{"id":"2501.18081","title":"Normative Evaluation of Large Language Models with Everyday Moral Dilemmas","created":"2025-01-30","cited_by_count":24,"area":null},{"id":"2206.07870","title":"How to talk so AI will learn: Instructions, descriptions, and autonomy","created":"2022-06-16","cited_by_count":22,"area":null},{"id":"2305.07970","title":"The Machine Psychology of Cooperation: Can GPT models operationalise prompts for altruism, cooperation, competitiveness and selfishness in economic games?","created":"2023-05-13","cited_by_count":22,"area":null},{"id":"2311.00710","title":"Interactive AI Alignment: Specification, Process, and Evaluation Alignment","created":"2023-10-23","cited_by_count":22,"area":null},{"id":"2406.03198","title":"The Impossibility of Fair LLMs","created":"2024-05-28","cited_by_count":22,"area":null},{"id":"2509.10147","title":"Virtual Agent Economies","created":"2025-09-12","cited_by_count":21,"area":null},{"id":"2210.02667","title":"A Human Rights-Based Approach to Responsible AI","created":"2022-10-06","cited_by_count":20,"area":null},{"id":"2405.11100","title":"Are Large Language Models Moral Hypocrites? A Study Based on Moral Foundations","created":"2024-05-17","cited_by_count":19,"area":null},{"id":"2112.01298","title":"Meaningful human control: actionable properties for AI system development","created":"2021-11-25","cited_by_count":18,"area":null},{"id":"2401.10352","title":"Bridging Cultural Nuances in Dialogue Agents through Cultural Value Surveys","created":"2024-01-18","cited_by_count":18,"area":null},{"id":"2404.04289","title":"Designing for Human-Agent Alignment: Understanding what humans want from their agents","created":"2024-04-04","cited_by_count":18,"area":null},{"id":"2505.08253","title":"Evaluating LLM Metrics Through Real-World Capabilities","created":"2025-05-13","cited_by_count":18,"area":null},{"id":"2405.19524","title":"AI Risk Management Should Incorporate Both Safety and Security","created":"2024-05-29","cited_by_count":17,"area":null},{"id":"2407.15366","title":"Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias","created":"2024-07-22","cited_by_count":17,"area":null},{"id":"2507.22608","title":"Language Arithmetics: Towards Systematic Language Neuron Identification and Manipulation","created":"2025-07-30","cited_by_count":17,"area":null},{"id":"2309.16639","title":"MindShift: Leveraging Large Language Models for Mental-States-Based Problematic Smartphone Use Intervention","created":"2023-09-28","cited_by_count":16,"area":null},{"id":"2405.17345","title":"Exploring and steering the moral compass of Large Language Models","created":"2024-05-27","cited_by_count":16,"area":null},{"id":"2411.06090","title":"Concept Bottleneck Language Models For protein design","created":"2024-11-09","cited_by_count":15,"area":null},{"id":"2206.04530","title":"DORA: Exploring Outlier Representations in Deep Neural Networks","created":"2022-06-09","cited_by_count":14,"area":null},{"id":"2306.00419","title":"Challenges and Remedies to Privacy and Security in AIGC: Exploring the Potential of Privacy Computing, Blockchain, and Beyond","created":"2023-06-01","cited_by_count":14,"area":null},{"id":"2205.09904","title":"Deep transfer learning for image classification: a survey","created":"2022-05-20","cited_by_count":13,"area":null},{"id":"2307.03201","title":"Scaling Laws Do Not Scale","created":"2023-07-05","cited_by_count":13,"area":null},{"id":"2405.08597","title":"Risks and Opportunities of Open-Source Generative AI","created":"2024-05-14","cited_by_count":13,"area":null},{"id":"2405.10729","title":"Contestable AI needs Computational Argumentation","created":"2024-05-17","cited_by_count":13,"area":null},{"id":"2405.15185","title":"An Evaluation of Estimative Uncertainty in Large Language Models","created":"2024-05-24","cited_by_count":13,"area":null},{"id":"2407.09241","title":"The Sociolinguistic Foundations of Language Modeling","created":"2024-07-12","cited_by_count":13,"area":null},{"id":"2504.18932","title":"AI Chatbots for Mental Health: Values and Harms from Lived Experiences of Depression","created":"2025-04-26","cited_by_count":13,"area":null},{"id":"2506.15047","title":"Mapping Caregiver Needs to AI Chatbot Design: Strengths and Gaps in Mental Health Support for Alzheimer's and Dementia Caregivers","created":"2025-06-18","cited_by_count":13,"area":null},{"id":"2204.05151","title":"Metaethical Perspectives on 'Benchmarking' AI Ethics","created":"2022-04-11","cited_by_count":12,"area":null},{"id":"2503.19598","title":"The Greatest Good Benchmark: Measuring LLMs' Alignment with Utilitarian Moral Dilemmas","created":"2025-03-25","cited_by_count":12,"area":null},{"id":"2512.16856","title":"Distributional AGI Safety","created":"2025-12-18","cited_by_count":12,"area":null},{"id":"2405.16714","title":"Crafting Interpretable Embeddings by Asking LLMs Questions","created":"2024-05-26","cited_by_count":11,"area":null},{"id":"2407.09221","title":"Evaluating AI Evaluation: Perils and Prospects","created":"2024-07-12","cited_by_count":11,"area":null},{"id":"2410.10398","title":"Are LLMs Socially Adaptive? Contrasting Belief Evolution in Large Language Models and Humans","created":"2024-10-14","cited_by_count":11,"area":null},{"id":"2509.08494","title":"HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants","created":"2025-09-10","cited_by_count":11,"area":null},{"id":"2512.19466","title":"Epistemological Fault Lines Between Human and Artificial Intelligence","created":"2025-12-22","cited_by_count":11,"area":null},{"id":"2305.02748","title":"A computational framework for human values","created":"2023-05-04","cited_by_count":10,"area":null},{"id":"2309.05030","title":"Decolonial AI Alignment: Openness, Vi\\'{s}e\\d{s}a-Dharma, and Including Excluded Knowledges","created":"2023-09-10","cited_by_count":10,"area":null},{"id":"2407.11733","title":"How Are LLMs Mitigating Stereotyping Harms? Learning from Search Engine Studies","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2408.16074","title":"Verification methods for international AI agreements","created":"2024-08-28","cited_by_count":10,"area":null},{"id":"2504.10143","title":"On the Value of Cross-Modal Misalignment in Multimodal Representation Learning","created":"2025-04-14","cited_by_count":10,"area":null},{"id":"2310.17551","title":"Unpacking the Ethical Value Alignment in Big Models","created":"2023-10-26","cited_by_count":9,"area":null},{"id":"2406.20087","title":"ProgressGym: Alignment with a Millennium of Moral Progress","created":"2024-06-28","cited_by_count":9,"area":null},{"id":"2503.00940","title":"Can AI Model the Complexities of Human Moral Decision-Making? A Qualitative Study of Kidney Allocation Decisions","created":"2025-03-02","cited_by_count":9,"area":null},{"id":"2107.09598","title":"Learning Altruistic Behaviours in Reinforcement Learning without External Rewards","created":"2021-07-20","cited_by_count":8,"area":null},{"id":"2310.06167","title":"Predictable Artificial Intelligence","created":"2023-10-09","cited_by_count":8,"area":null},{"id":"2402.14679","title":"Is Self-knowledge and Action Consistent or Not: Investigating Large Language Model's Personality","created":"2024-02-22","cited_by_count":8,"area":null},{"id":"2406.04231","title":"Quantifying Misalignment Between Agents: Towards a Sociotechnical Understanding of Alignment","created":"2024-06-06","cited_by_count":8,"area":null},{"id":"2501.02039","title":"An Investigation into Value Misalignment in LLM-Generated Texts for Cultural Heritage","created":"2025-01-03","cited_by_count":8,"area":null},{"id":"2506.17434","title":"Resource Rational Contractualism Should Guide AI Alignment","created":"2025-06-20","cited_by_count":8,"area":null},{"id":"2205.04279","title":"Aligned with Whom? Direct and social goals for AI systems","created":"2022-05-09","cited_by_count":7,"area":null},{"id":"2206.02841","title":"Researching Alignment Research: Unsupervised Analysis","created":"2022-06-06","cited_by_count":7,"area":null},{"id":"2206.08966","title":"Actionable Guidance for High-Consequence AI Risk Management: Towards Standards Addressing AI Catastrophic Risks","created":"2022-06-17","cited_by_count":7,"area":null},{"id":"2306.06767","title":"The Impact of ChatGPT and LLMs on Medical Imaging Stakeholders: Perspectives and Use Cases","created":"2023-06-11","cited_by_count":7,"area":null},{"id":"2310.02457","title":"The Empty Signifier Problem: Towards Clearer Paradigms for Operationalising \"Alignment\" in Large Language Models","created":"2023-10-03","cited_by_count":7,"area":null},{"id":"2401.17228","title":"Morality is Non-Binary: Building a Pluralist Moral Sentence Embedding Space using Contrastive Learning","created":"2024-01-30","cited_by_count":7,"area":null},{"id":"2402.16751","title":"Value Preferences Estimation and Disambiguation in Hybrid Participatory Systems","created":"2024-02-26","cited_by_count":7,"area":null},{"id":"2506.14196","title":"Balancing Caregiving and Self-Care: Exploring Mental Health Needs of Alzheimer's and Dementia Caregivers","created":"2025-06-17","cited_by_count":7,"area":null},{"id":"2512.01351","title":"Benchmarking Overton Pluralism in LLMs","created":"2025-12-01","cited_by_count":7,"area":null},{"id":"2102.04255","title":"AI Development for the Public Interest: From Abstraction Traps to Sociotechnical Risks","created":"2021-02-04","cited_by_count":6,"area":null},{"id":"2112.08256","title":"Est-ce que vous compute? Code-switching, cultural identity, and AI","created":"2021-12-15","cited_by_count":6,"area":null},{"id":"2405.11612","title":"Sociotechnical Implications of Generative Artificial Intelligence for Information Access","created":"2024-05-19","cited_by_count":6,"area":null},{"id":"2407.12393","title":"PersLLM: A Personified Training Approach for Large Language Models","created":"2024-07-17","cited_by_count":6,"area":null}],"next_cursor":"100"}