{"list":"other","total":82,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439},{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"2305.19118","title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate","created":"2023-05-30","cited_by_count":1011},{"id":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912},{"id":"1609.05807","title":"Inherent Trade-Offs in the Fair Determination of Risk Scores","created":"2016-09-19","cited_by_count":586},{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557},{"id":"2410.05229","title":"GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models","created":"2024-10-07","cited_by_count":550},{"id":"2001.09768","title":"Artificial Intelligence, Values and Alignment","created":"2020-01-13","cited_by_count":448},{"id":"2310.11667","title":"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents","created":"2023-10-18","cited_by_count":367},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328},{"id":"1902.10486","title":"On Tiny Episodic Memories in Continual Learning","created":"2019-02-27","cited_by_count":307},{"id":"2405.00675","title":"Self-Play Preference Optimization for Language Model Alignment","created":"2024-05-01","cited_by_count":232},{"id":"2006.06958","title":"Understanding the Role of Training Regimes in Continual Learning","created":"2020-06-12","cited_by_count":180},{"id":"2404.03715","title":"Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences","created":"2024-04-04","cited_by_count":178},{"id":"2310.00746","title":"RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models","created":"2023-10-01","cited_by_count":175},{"id":"2402.18571","title":"Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards","created":"2024-02-28","cited_by_count":148},{"id":"2003.09553","title":"Adversarial Continual Learning","created":"2020-03-21","cited_by_count":142},{"id":"2402.08925","title":"MaxMin-RLHF: Alignment with Diverse Human Preferences","created":"2024-02-14","cited_by_count":123},{"id":"2403.01244","title":"Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal","created":"2024-03-02","cited_by_count":118},{"id":"2402.07510","title":"Secret Collusion among AI Agents: Multi-Agent Deception via Steganography","created":"2024-02-12","cited_by_count":113},{"id":"2406.04836","title":"Revisiting Catastrophic Forgetting in Large Language Model Tuning","created":"2024-06-07","cited_by_count":99},{"id":"2309.17234","title":"Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation","created":"2023-09-29","cited_by_count":96},{"id":"2405.20304","title":"Group Robust Preference Optimization in Reward-free RLHF","created":"2024-05-30","cited_by_count":95},{"id":"2312.05488","title":"Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysis","created":"2023-12-09","cited_by_count":92},{"id":"2403.08635","title":"Human Alignment of Large Language Models through Online Preference Optimisation","created":"2024-03-13","cited_by_count":91},{"id":"2404.10642","title":"Self-playing Adversarial Language Game Enhances LLM Reasoning","created":"2024-04-16","cited_by_count":83},{"id":"2402.02030","title":"Panacea: Pareto Alignment via Preference Adaptation for LLMs","created":"2024-02-03","cited_by_count":80},{"id":"2404.16767","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","created":"2024-04-25","cited_by_count":69},{"id":"2402.07314","title":"Online Iterative Reinforcement Learning from Human Feedback with General Preference Model","created":"2024-02-11","cited_by_count":52},{"id":"2309.05898","title":"Strategic Behavior of Large Language Models: Game Structure vs. Contextual Framing","created":"2023-09-12","cited_by_count":51},{"id":"2409.02387","title":"Large Language Models and Cognitive Science: A Comprehensive Review of Similarities, Differences, and Challenges","created":"2024-09-04","cited_by_count":49},{"id":"2401.04536","title":"Evaluating Language Model Agency through Negotiations","created":"2024-01-09","cited_by_count":48},{"id":"2402.15813","title":"Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Method","created":"2024-02-24","cited_by_count":48},{"id":"2407.00617","title":"Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning","created":"2024-06-30","cited_by_count":45},{"id":"2407.15762","title":"Conditional Language Policy: A General Framework for Steerable Multi-Objective Finetuning","created":"2024-07-22","cited_by_count":43},{"id":"2504.19162","title":"SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning","created":"2025-04-27","cited_by_count":42},{"id":"2506.07468","title":"Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models","created":"2025-06-09","cited_by_count":39},{"id":"2508.15361","title":"A Survey on Large Language Model Benchmarks","created":"2025-08-21","cited_by_count":36},{"id":"2505.12923","title":"The Traitors: Deception and Trust in Multi-Agent Language Model Simulations","created":"2025-05-19","cited_by_count":34},{"id":"2403.05006","title":"Provable Pluralistic Alignment: Multi-Party RLHF under Offline Human Feedback","created":"2024-03-08","cited_by_count":32},{"id":"2505.17147","title":"MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming","created":"2025-05-22","cited_by_count":32},{"id":"2402.01704","title":"Steering Language Models with Game-Theoretic Solvers","created":"2024-01-24","cited_by_count":28},{"id":"2410.10479","title":"TMGBench: A Systematic Game Benchmark for Evaluating Strategic Reasoning Abilities of LLMs","created":"2024-10-14","cited_by_count":24},{"id":"2502.16852","title":"Improving LLM General Preference Alignment via Optimistic Online Mirror Descent","created":"2025-02-24","cited_by_count":24},{"id":"2405.15065","title":"Direct Preference Optimization With Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences","created":"2024-05-23","cited_by_count":23},{"id":"2407.07796","title":"Evaluating Large Language Models with Grid-Based Game Competitions: An Extensible LLM Benchmark and Leaderboard","created":"2024-07-10","cited_by_count":22},{"id":"2503.00295","title":"Robust Multi-Objective Preference Alignment with Online DPO","created":"2025-03-01","cited_by_count":22},{"id":"2502.12504","title":"Simulating Cooperative Prosocial Behavior with Multi-Agent LLMs: Evidence and Mechanisms for AI Agents to Inform Policy Decisions","created":"2025-02-18","cited_by_count":20},{"id":"2206.13477","title":"Parametrically Retargetable Decision-Makers Tend To Seek Power","created":"2022-06-27","cited_by_count":19},{"id":"2502.05163","title":"Enhancing LLM Safety Through a Theoretical Minimax Game Lens","created":"2025-02-07","cited_by_count":19},{"id":"2405.16276","title":"Mechanism Design for LLM Fine-tuning with Multiple Reward Models","created":"2024-05-25","cited_by_count":18},{"id":"2310.00322","title":"Evolving Diverse Red-team Language Models in Multi-round Multi-agent Games","created":"2023-09-30","cited_by_count":17},{"id":"2406.04274","title":"Self-Play with Adversarial Critic: Provable and Scalable Offline Alignment for Language Models","created":"2024-06-06","cited_by_count":16},{"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":"2406.10977","title":"Toward Optimal LLM Alignments Using Two-Player Games","created":"2024-06-16","cited_by_count":13},{"id":"2505.10892","title":"Multi-Objective Preference Optimization: Improving Human Alignment of Generative Models","created":"2025-05-16","cited_by_count":13},{"id":"2502.15145","title":"Projection Optimization: A General Framework for Multi-Objective and Multi-Group RLHF","created":"2025-02-21","cited_by_count":11},{"id":"2412.16834","title":"Online Learning from Strategic Human Feedback in LLM Fine-Tuning","created":"2024-12-22","cited_by_count":10},{"id":"2502.18099","title":"Stackelberg Self-Annotation: A Robust Approach to Data-Efficient LLM Alignment","created":"2025-02-25","cited_by_count":10},{"id":"2504.19276","title":"Anyprefer: An Agentic Framework for Preference Data Synthesis","created":"2025-04-27","cited_by_count":10},{"id":"2505.20627","title":"Fundamental Limits of Game-Theoretic LLM Alignment: Smith Consistency and Preference Matching","created":"2025-05-27","cited_by_count":10},{"id":"2512.16626","title":"Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential Game","created":"2025-12-18","cited_by_count":10},{"id":"2505.13636","title":"Incentivizing Truthful Language Models via Peer Elicitation Games","created":"2025-05-19","cited_by_count":9},{"id":"2506.04721","title":"SPARTA ALIGNMENT: Collectively Aligning Multiple Language Models through Combat","created":"2025-06-05","cited_by_count":9},{"id":"2410.23223","title":"COMAL: A Convergent Meta-Algorithm for Aligning LLMs with General Preferences","created":"2024-10-30","cited_by_count":8},{"id":"2412.16772","title":"Assessing Social Alignment: Do Personality-Prompted Large Language Models Behave Like Humans?","created":"2024-12-21","cited_by_count":8},{"id":"2502.12598","title":"Bring Your Own Knowledge: A Survey of Methods for LLM Knowledge Expansion","created":"2025-02-18","cited_by_count":8},{"id":"2601.08462","title":"M3-BENCH: Process-Aware Evaluation of LLM Agents' Social Behaviors in Mixed-Motive Games","created":"2026-01-13","cited_by_count":8},{"id":"2502.18293","title":"AMPO: Active Multi-Preference Optimization for Self-play Preference Selection","created":"2025-02-25","cited_by_count":5},{"id":"2506.05619","title":"Beyond RLHF and NLHF: Population-Proportional Alignment under an Axiomatic Framework","created":"2025-06-05","cited_by_count":4},{"id":"2407.12461","title":"Compatibility of Fairness and Nash Welfare under Subadditive Valuations","created":"2024-07-17","cited_by_count":3},{"id":"2406.15890","title":"Language Alignment via Nash-learning and Adaptive feedback","created":"2024-06-22","cited_by_count":2},{"id":"2412.15114","title":"Towards Friendly AI: A Comprehensive Review and New Perspectives on Human-AI Alignment","created":"2024-12-19","cited_by_count":2},{"id":"2502.01127","title":"The Battling Influencers Game: Nash Equilibria Structure of a Potential Game and Implications to Value Alignment","created":"2025-02-03","cited_by_count":1}],"next_cursor":null}