{"total":93,"rows":[{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429,"area":"agents"},{"id":"2310.17884","title":"Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory","created":"2023-10-27","cited_by_count":230,"area":null},{"id":"2307.14324","title":"Evaluating the Moral Beliefs Encoded in LLMs","created":"2023-07-26","cited_by_count":215,"area":null},{"id":"2505.23836","title":"Large Language Models Often Know When They Are Being Evaluated","created":"2025-05-28","cited_by_count":128,"area":null},{"id":"2404.16698","title":"Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents","created":"2024-04-25","cited_by_count":125,"area":"wm"},{"id":"2306.00622","title":"ReviewerGPT? An Exploratory Study on Using Large Language Models for Paper Reviewing","created":"2023-06-01","cited_by_count":122,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2303.05453","title":"Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback","created":"2023-03-09","cited_by_count":87,"area":"alignment"},{"id":"2404.05399","title":"SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety","created":"2024-04-08","cited_by_count":77,"area":"safety"},{"id":"2410.02683","title":"DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life","created":"2024-10-03","cited_by_count":59,"area":null},{"id":"2310.07629","title":"The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values","created":"2023-10-11","cited_by_count":54,"area":"alignment"},{"id":"2406.17626","title":"CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference","created":"2024-06-25","cited_by_count":51,"area":"safety"},{"id":"2408.16984","title":"Beyond Preferences in AI Alignment","created":"2024-08-30","cited_by_count":49,"area":"alignment"},{"id":"2303.04222","title":"SemEval-2023 Task 10: Explainable Detection of Online Sexism","created":"2023-03-07","cited_by_count":48,"area":null},{"id":"2405.14125","title":"ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation","created":"2024-05-23","cited_by_count":47,"area":"agents"},{"id":"2407.02273","title":"Language Model Alignment in Multilingual Trolley Problems","created":"2024-07-02","cited_by_count":46,"area":"alignment"},{"id":"2308.12014","title":"From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models","created":"2023-08-23","cited_by_count":45,"area":"alignment"},{"id":"2310.19677","title":"MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks","created":"2023-10-30","cited_by_count":44,"area":"alignment"},{"id":"2306.07075","title":"Large Language Models as Tax Attorneys: A Case Study in Legal Capabilities Emergence","created":"2023-06-12","cited_by_count":42,"area":null},{"id":"2310.10077","title":"Prompt Packer: Deceiving LLMs through Compositional Instruction with Hidden Attacks","created":"2023-10-16","cited_by_count":35,"area":"safety"},{"id":"2309.12444","title":"Foundation Metrics for Evaluating Effectiveness of Healthcare Conversations Powered by Generative AI","created":"2023-09-21","cited_by_count":32,"area":null},{"id":"2401.11839","title":"AI for social science and social science of AI: A Survey","created":"2024-01-22","cited_by_count":29,"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":"2410.23426","title":"Social Science Meets LLMs: How Reliable Are Large Language Models in Social Simulations?","created":"2024-10-30","cited_by_count":26,"area":null},{"id":"2406.11096","title":"The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models","created":"2024-06-16","cited_by_count":19,"area":null},{"id":"2303.06074","title":"Susceptibility to Influence of Large Language Models","created":"2023-03-10","cited_by_count":17,"area":null},{"id":"2306.00784","title":"Interpretable Math Word Problem Solution Generation Via Step-by-step Planning","created":"2023-06-01","cited_by_count":17,"area":null},{"id":"2310.15431","title":"What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations","created":"2023-10-24","cited_by_count":15,"area":null},{"id":"2505.19212","title":"When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas","created":"2025-05-25","cited_by_count":15,"area":null},{"id":"2310.13915","title":"Values, Ethics, Morals? On the Use of Moral Concepts in NLP Research","created":"2023-10-21","cited_by_count":14,"area":null},{"id":"2502.14083","title":"Are Rules Meant to be Broken? Understanding Multilingual Moral Reasoning as a Computational Pipeline with UniMoral","created":"2025-02-19","cited_by_count":14,"area":"lr"},{"id":"2505.18154","title":"The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas","created":"2025-05-23","cited_by_count":13,"area":"lr"},{"id":"2403.14659","title":"Social Intelligence Data Infrastructure: Structuring the Present and Navigating the Future","created":"2024-02-28","cited_by_count":11,"area":null},{"id":"2408.09819","title":"CMoralEval: A Moral Evaluation Benchmark for Chinese Large Language Models","created":"2024-08-19","cited_by_count":10,"area":null},{"id":"2506.13082","title":"Discerning What Matters: A Multi-Dimensional Assessment of Moral Competence in LLMs","created":"2025-06-16","cited_by_count":10,"area":null},{"id":"2305.02626","title":"\"Oops, Did I Just Say That?\" Testing and Repairing Unethical Suggestions of Large Language Models with Suggest-Critique-Reflect Process","created":"2023-05-04","cited_by_count":9,"area":null},{"id":"2306.08651","title":"Toward Grounded Commonsense Reasoning","created":"2023-06-14","cited_by_count":9,"area":"lr"},{"id":"2409.13354","title":"Recent Advancement of Emotion Cognition in Large Language Models","created":"2024-09-20","cited_by_count":9,"area":null},{"id":"2412.20718","title":"MM-MoralBench: A MultiModal Moral Evaluation Benchmark for Large Vision-Language Models","created":"2024-12-30","cited_by_count":9,"area":"mllm"},{"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":"2210.10332","title":"Revision Transformers: Instructing Language Models to Change their Values","created":"2022-10-19","cited_by_count":8,"area":null},{"id":"2306.11432","title":"Towards Theory-based Moral AI: Moral AI with Aggregating Models Based on Normative Ethical Theory","created":"2023-06-20","cited_by_count":8,"area":null},{"id":"2310.10418","title":"Reading Books is Great, But Not if You Are Driving! Visually Grounded Reasoning about Defeasible Commonsense Norms","created":"2023-10-16","cited_by_count":8,"area":"lr"},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","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":"2307.00660","title":"Minimum Levels of Interpretability for Artificial Moral Agents","created":"2023-07-02","cited_by_count":5,"area":null},{"id":"2402.02547","title":"Integration of cognitive tasks into artificial general intelligence test for large models","created":"2024-02-04","cited_by_count":5,"area":null},{"id":"2406.09464","title":"GPT-ology, Computational Models, Silicon Sampling: How should we think about LLMs in Cognitive Science?","created":"2024-06-13","cited_by_count":5,"area":"lr"},{"id":"2502.03397","title":"SPRI: Aligning Large Language Models with Context-Situated Principles","created":"2025-02-05","cited_by_count":5,"area":"alignment"},{"id":"2506.09656","title":"Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives","created":"2025-06-11","cited_by_count":5,"area":"agents"},{"id":"2310.00378","title":"ValueDCG: Measuring Comprehensive Human Value Understanding Ability of Language Models","created":"2023-09-30","cited_by_count":4,"area":null},{"id":"2402.14258","title":"Eagle: Ethical Dataset Given from Real Interactions","created":"2024-02-22","cited_by_count":4,"area":null},{"id":"2404.10975","title":"Procedural Dilemma Generation for Evaluating Moral Reasoning in Humans and Language Models","created":"2024-04-17","cited_by_count":4,"area":"lr"},{"id":"2410.08698","title":"SocialGaze: Improving the Integration of Human Social Norms in Large Language Models","created":"2024-10-11","cited_by_count":4,"area":"lr"},{"id":"2503.02976","title":"Teaching AI to Handle Exceptions: Supervised Fine-Tuning with Human-Aligned Judgment","created":"2025-03-04","cited_by_count":4,"area":"agents"},{"id":"2503.11348","title":"RESPONSE: Benchmarking the Ability of Language Models to Undertake Commonsense Reasoning in Crisis Situation","created":"2025-03-14","cited_by_count":4,"area":"lr"},{"id":"2509.21443","title":"One Model, Many Morals: Uncovering Cross-Linguistic Misalignments in Computational Moral Reasoning","created":"2025-09-25","cited_by_count":4,"area":"lr"},{"id":"2509.25897","title":"RoleConflictBench: A Benchmark of Role Conflict Scenarios for Evaluating LLMs' Contextual Sensitivity","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2604.05339","title":"Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities","created":"2026-04-07","cited_by_count":4,"area":"agents"},{"id":"2308.12578","title":"Mind vs. Mouth: On Measuring Re-judge Inconsistency of Social Bias in Large Language Models","created":"2023-08-24","cited_by_count":3,"area":null},{"id":"2310.05563","title":"STREAM: Social data and knowledge collective intelligence platform for TRaining Ethical AI Models","created":"2023-10-09","cited_by_count":3,"area":null},{"id":"2402.13709","title":"SaGE: Evaluating Moral Consistency in Large Language Models","created":"2024-02-21","cited_by_count":3,"area":null},{"id":"2409.13521","title":"A Survey on Moral Foundation Theory and Pre-Trained Language Models: Current Advances and Challenges","created":"2024-09-20","cited_by_count":3,"area":null},{"id":"2410.15311","title":"Who is Undercover? Guiding LLMs to Explore Multi-Perspective Team Tactic in the Game","created":"2024-10-20","cited_by_count":3,"area":null},{"id":"2506.01495","title":"C-VARC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Models","created":"2025-06-02","cited_by_count":3,"area":"alignment"},{"id":"2510.06370","title":"EVALUESTEER: Measuring Reward Model Steerability Towards Values and Preferences","created":"2025-10-07","cited_by_count":3,"area":"alignment"},{"id":"2601.03699","title":"RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models","created":"2026-01-07","cited_by_count":3,"area":"safety"},{"id":"2603.23114","title":"On the Context Sensitivity of LLM Moral Judgment","created":"2026-03-24","cited_by_count":3,"area":null},{"id":"2312.03726","title":"Interpretation modeling: Social grounding of sentences by reasoning over their implicit moral judgments","created":"2023-11-27","cited_by_count":2,"area":null},{"id":"2506.00079","title":"Who Gets the Kidney? Human-AI Alignment, Indecision, and Moral Values","created":"2025-05-30","cited_by_count":2,"area":"alignment"},{"id":"2508.12754","title":"Beyond Ethical Alignment: Evaluating LLMs as Artificial Moral Assistants","created":"2025-08-18","cited_by_count":2,"area":null},{"id":"2510.11222","title":"Fairness Metric Design Exploration in Multi-Domain Moral Sentiment Classification using Transformer-Based Models","created":"2025-10-13","cited_by_count":2,"area":null},{"id":"2604.06233","title":"Blind Refusal: Language Models Refuse to Help Users Evade Unjust, Absurd, and Illegitimate Rules","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2604.19125","title":"Do Emotions Influence Moral Judgment in Large Language Models?","created":"2026-04-21","cited_by_count":2,"area":null},{"id":"2512.15793","title":"Explainable Ethical Assessment on Human Behaviors by Generating Conflicting Social Norms","created":"2025-12-16","cited_by_count":1,"area":null},{"id":"2602.00851","title":"Persuasion Propagation: Does Persuasion Change AI Agent Behavior?","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2603.16017","title":"Understanding Moral Reasoning Trajectories in Large Language Models: Toward Probing-Based Explainability","created":"2026-03-16","cited_by_count":1,"area":"lr"},{"id":"2606.11232","title":"Every Act Has Its Price: Compressed Moral Composition in Frontier LLMs","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2607.05552","title":"The yes-no bias of large language models reflects answer order and wording, not shifts in moral judgment","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2412.12848","title":"ClarityEthic: Explainable Moral Judgment Utilizing Contrastive Ethical Insights from Large Language Models","created":"2024-12-17","cited_by_count":0,"area":null},{"id":"2501.00885","title":"Representation in large language models","created":"2025-01-01","cited_by_count":0,"area":null},{"id":"2504.11473","title":"Visual moral inference and communication","created":"2025-04-12","cited_by_count":0,"area":null},{"id":"2605.03936","title":"The Counterexample Game: Iterated Conceptual Analysis and Repair in Language Models","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.08221","title":"NoisyCoconut: Counterfactual Consensus via Latent Space Reasoning","created":"2026-05-06","cited_by_count":0,"area":"lr"},{"id":"2606.05890","title":"Staying with the Uncertainty: Uncertainty-Scaffolding Strategies for Artificial Moral Advisors in LLM-to-LLM Simulated Conversations","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.13282","title":"ERTS: Adversarial Robustness Testing of Ethical AI via Semantic Perturbation in a Bounded Consequence Space","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.31213","title":"Can LLMs Imagine Moral Alternatives Beyond Binary Dilemmas?","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.11736","title":"MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning","created":"2026-07-13","cited_by_count":0,"area":"lr"},{"id":"2607.17946","title":"A Geometric Perspective on Stabilizing Value Conflict Resolution","created":"2026-07-20","cited_by_count":0,"area":"alignment"},{"id":"2608.28610","title":"TPvG: A Moral Decision Framework for Large Language Models from One-Shot to Sequential Feedback","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2609.01611","title":"EvalDetectBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2609.05088","title":"Measuring AI Accountability Through Argumentation Analysis: Can Model Reasoning Withstand Scrutiny?","created":"2026-09-04","cited_by_count":0,"area":"lr"},{"id":"2609.38260","title":"ContextAdapt: Evaluating Contextual Adaptation and Value Alignment in LLMs","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}