{"list":"other","total":52,"rows":[{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"2606.19348","title":"DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence","created":"2026-04-26","cited_by_count":1040},{"id":"2303.17548","title":"Whose Opinions Do Language Models Reflect?","created":"2023-03-30","cited_by_count":773},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2209.06899","title":"Out of One, Many: Using Language Models to Simulate Human Samples","created":"2022-09-14","cited_by_count":752},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"2308.01263","title":"XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models","created":"2023-08-02","cited_by_count":505},{"id":"2501.14249","title":"Humanity's Last Exam","created":"2025-01-24","cited_by_count":491},{"id":"2001.09768","title":"Artificial Intelligence, Values and Alignment","created":"2020-01-13","cited_by_count":448},{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437},{"id":"2310.06452","title":"Understanding the Effects of RLHF on LLM Generalisation and Diversity","created":"2023-10-10","cited_by_count":396},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284},{"id":"2505.11831","title":"ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems","created":"2025-05-17","cited_by_count":190},{"id":"2302.00560","title":"Co-Writing with Opinionated Language Models Affects Users' Views","created":"2023-02-01","cited_by_count":148},{"id":"2510.22954","title":"Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)","created":"2025-10-27","cited_by_count":141},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136},{"id":"2312.08358","title":"Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF","created":"2023-12-13","cited_by_count":133},{"id":"2505.13995","title":"ELEPHANT: Measuring and understanding social sycophancy in LLMs","created":"2025-05-20","cited_by_count":129},{"id":"2403.14380","title":"On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial","created":"2024-03-21","cited_by_count":109},{"id":"2401.06730","title":"Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertainty","created":"2024-01-12","cited_by_count":106},{"id":"2101.05853","title":"Algorithmic Monoculture and Social Welfare","created":"2021-01-14","cited_by_count":100},{"id":"2211.13972","title":"Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?","created":"2022-11-25","cited_by_count":91},{"id":"2306.11247","title":"DICES Dataset: Diversity in Conversational AI Evaluation for Safety","created":"2023-06-20","cited_by_count":86},{"id":"2102.03896","title":"Consequences of Misaligned AI","created":"2021-02-07","cited_by_count":80},{"id":"2402.15018","title":"Unintended Impacts of LLM Alignment on Global Representation","created":"2024-02-22","cited_by_count":66},{"id":"2406.08469","title":"PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferences","created":"2024-06-12","cited_by_count":54},{"id":"2410.08968","title":"Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements","created":"2024-10-11","cited_by_count":36},{"id":"2101.06060","title":"The Challenge of Value Alignment: from Fairer Algorithms to AI Safety","created":"2021-01-15","cited_by_count":35},{"id":"2410.19803","title":"First-Person Fairness in Chatbots","created":"2024-10-16","cited_by_count":20},{"id":"2510.06084","title":"Spectrum Tuning: Post-Training for Distributional Coverage and In-Context Steerability","created":"2025-10-07","cited_by_count":20},{"id":"2402.01705","title":"Beyond Behaviorist Representational Harms: A Plan for Measurement and Mitigation","created":"2024-01-25","cited_by_count":17},{"id":"2502.13775","title":"VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcare","created":"2025-02-19","cited_by_count":17},{"id":"2412.04629","title":"Argumentative Experience: Reducing Confirmation Bias on Controversial Issues through LLM-Generated Multi-Persona Debates","created":"2024-12-05","cited_by_count":15},{"id":"2411.03665","title":"Evaluating Moral Beliefs across LLMs through a Pluralistic Framework","created":"2024-11-06","cited_by_count":11},{"id":"2506.06166","title":"The Lock-in Hypothesis: Stagnation by Algorithm","created":"2025-06-06","cited_by_count":11},{"id":"2501.12619","title":"Quantification of Large Language Model Distillation","created":"2025-01-22","cited_by_count":9},{"id":"2509.02464","title":"SpecEval: Evaluating Model Adherence to Behavior Specifications","created":"2025-09-02","cited_by_count":9},{"id":"2512.01351","title":"Benchmarking Overton Pluralism in LLMs","created":"2025-12-01","cited_by_count":7},{"id":"2512.03399","title":"Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value","created":"2025-12-03","cited_by_count":6},{"id":"2512.01166","title":"Evaluating AI Providers' Frontier Safety Frameworks","created":"2025-12-01","cited_by_count":3},{"id":"2602.08716","title":"PERSPECTRA: A Scalable and Configurable Pluralist Benchmark of Perspectives from Arguments","created":"2026-02-09","cited_by_count":3},{"id":"2604.07190","title":"The ATOM Report: Measuring the Open Language Model Ecosystem","created":"2026-04-08","cited_by_count":2},{"id":"2605.12120","title":"To Whom Do Language Models Align? Measuring Principal Hierarchies Under High-Stakes Competing Demands","created":"2026-05-12","cited_by_count":2},{"id":"2605.18738","title":"What Does the AI Doctor Value? Auditing Pluralism in the Clinical Ethics of Language Models","created":"2026-05-18","cited_by_count":2},{"id":"2605.28911","title":"Political Neutrality as Balanced Approval: A Large-Scale Human Evaluation of AI Responses","created":"2026-05-27","cited_by_count":2},{"id":"2602.20759","title":"Overton Pluralistic Reinforcement Learning for Large Language Models","created":"2026-02-24","cited_by_count":1},{"id":"2605.16245","title":"AI-Mediated Communication Can Steer Collective Opinion","created":"2026-05-15","cited_by_count":1},{"id":"2607.18506","title":"AI Value Alignment for Evolving Social Norms","created":"2026-07-20","cited_by_count":1}],"next_cursor":null}