{"list":"other","total":61,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2307.04657","title":"BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset","created":"2023-07-10","cited_by_count":860},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"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":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"2404.13208","title":"The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions","created":"2024-04-19","cited_by_count":493},{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437},{"id":"2410.09024","title":"AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents","created":"2024-10-11","cited_by_count":437},{"id":"2108.09293","title":"Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions","created":"2021-08-20","cited_by_count":431},{"id":"2412.14470","title":"Agent-SafetyBench: Evaluating the Safety of LLM Agents","created":"2024-12-19","cited_by_count":306},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292},{"id":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243},{"id":"1402.0590","title":"A Survey of Multi-Objective Sequential Decision-Making","created":"2014-02-04","cited_by_count":242},{"id":"2305.10142","title":"Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback","created":"2023-05-17","cited_by_count":207},{"id":"2309.07045","title":"SafetyBench: Evaluating the Safety of Large Language Models","created":"2023-09-13","cited_by_count":199},{"id":"2402.10207","title":"Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment","created":"2024-02-15","cited_by_count":175},{"id":"2310.03708","title":"Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization","created":"2023-10-05","cited_by_count":124},{"id":"2202.02950","title":"Jury Learning: Integrating Dissenting Voices into Machine Learning Models","created":"2022-02-07","cited_by_count":118},{"id":"2007.02423","title":"Participation is not a Design Fix for Machine Learning","created":"2020-07-05","cited_by_count":111},{"id":"2309.00779","title":"Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties","created":"2023-09-02","cited_by_count":97},{"id":"1906.02386","title":"Deep Reinforcement Learning for Multi-objective Optimization","created":"2019-06-06","cited_by_count":90},{"id":"2310.00907","title":"The Participatory Turn in AI Design: Theoretical Foundations and the Current State of Practice","created":"2023-10-02","cited_by_count":87},{"id":"2401.16745","title":"MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models","created":"2024-01-30","cited_by_count":81},{"id":"2406.18682","title":"The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm","created":"2024-06-26","cited_by_count":70},{"id":"2310.11523","title":"Group Preference Optimization: Few-Shot Alignment of Large Language Models","created":"2023-10-17","cited_by_count":63},{"id":"2503.00172","title":"A Survey of Uncertainty Estimation Methods on Large Language Models","created":"2025-02-28","cited_by_count":62},{"id":"2405.12063","title":"CLAMBER: A Benchmark of Identifying and Clarifying Ambiguous Information Needs in Large Language Models","created":"2024-05-20","cited_by_count":54},{"id":"2403.17141","title":"MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models","created":"2024-03-25","cited_by_count":44},{"id":"2309.01291","title":"Generative Social Choice","created":"2023-09-03","cited_by_count":43},{"id":"2109.12480","title":"Explainability Pitfalls: Beyond Dark Patterns in Explainable AI","created":"2021-09-26","cited_by_count":36},{"id":"2410.08968","title":"Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements","created":"2024-10-11","cited_by_count":36},{"id":"2401.16332","title":"Tradeoffs Between Alignment and Helpfulness in Language Models with Steering Methods","created":"2024-01-29","cited_by_count":28},{"id":"2311.00710","title":"Interactive AI Alignment: Specification, Process, and Evaluation Alignment","created":"2023-10-23","cited_by_count":22},{"id":"2506.04018","title":"AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents","created":"2025-06-04","cited_by_count":22},{"id":"2409.09603","title":"Towards Data-Centric RLHF: Simple Metrics for Preference Dataset Comparison","created":"2024-09-15","cited_by_count":21},{"id":"2508.07768","title":"Pareto Multi-Objective Alignment for Language Models","created":"2025-08-11","cited_by_count":20},{"id":"2404.14068","title":"Holistic Safety and Responsibility Evaluations of Advanced AI Models","created":"2024-04-22","cited_by_count":19},{"id":"2509.01909","title":"Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models","created":"2025-09-02","cited_by_count":19},{"id":"2502.14354","title":"Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment","created":"2025-02-20","cited_by_count":16},{"id":"2307.02842","title":"Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback","created":"2023-07-06","cited_by_count":14},{"id":"2505.20925","title":"Multi-objective Large Language Model Alignment with Hierarchical Experts","created":"2025-05-27","cited_by_count":13},{"id":"2505.24846","title":"MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning","created":"2025-05-30","cited_by_count":11},{"id":"2602.02455","title":"Drift-Bench: Diagnosing Cooperative Breakdowns in LLM Agents under Input Faults via Multi-Turn Interaction","created":"2026-02-02","cited_by_count":9},{"id":"2501.06911","title":"Risk-Averse Finetuning of Large Language Models","created":"2025-01-12","cited_by_count":7},{"id":"2512.01351","title":"Benchmarking Overton Pluralism in LLMs","created":"2025-12-01","cited_by_count":7},{"id":"2410.11221","title":"Multi-objective Reinforcement Learning: A Tool for Pluralistic Alignment","created":"2024-10-15","cited_by_count":4},{"id":"2510.08044","title":"Towards Reliable LLM-based Robot Planning via Combined Uncertainty Estimation","created":"2025-10-09","cited_by_count":4},{"id":"2405.03387","title":"The high dimensional psychological profile and cultural bias of ChatGPT","created":"2024-05-06","cited_by_count":2},{"id":"2410.12194","title":"Negative-Prompt-driven Alignment for Generative Language Model","created":"2024-10-16","cited_by_count":2},{"id":"2511.20072","title":"MTA: A Merge-then-Adapt Framework for Personalized Large Language Model","created":"2025-11-25","cited_by_count":2}],"next_cursor":null}