{"list":"other","total":66,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2401.10020","title":"Self-Rewarding Language Models","created":"2024-01-18","cited_by_count":681},{"id":"1605.06676","title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning","created":"2016-05-21","cited_by_count":575},{"id":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562},{"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":"2401.05566","title":"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training","created":"2024-01-10","cited_by_count":529},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499},{"id":"2401.08417","title":"Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation","created":"2024-01-16","cited_by_count":394},{"id":"2412.14093","title":"Alignment faking in large language models","created":"2024-12-18","cited_by_count":360},{"id":"2404.12358","title":"From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function","created":"2024-04-18","cited_by_count":242},{"id":"2306.14898","title":"InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback","created":"2023-06-26","cited_by_count":238},{"id":"2402.19446","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","created":"2024-02-29","cited_by_count":228},{"id":"2312.00886","title":"Nash Learning from Human Feedback","created":"2023-12-01","cited_by_count":224},{"id":"2406.01171","title":"Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization","created":"2024-06-03","cited_by_count":208},{"id":"2403.02502","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","created":"2024-03-04","cited_by_count":197},{"id":"1908.04734","title":"Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspective","created":"2019-08-13","cited_by_count":108},{"id":"2403.19154","title":"STaR-GATE: Teaching Language Models to Ask Clarifying Questions","created":"2024-03-28","cited_by_count":104},{"id":"1802.08979","title":"NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System","created":"2018-02-25","cited_by_count":98},{"id":"1611.08219","title":"The Off-Switch Game","created":"2016-11-24","cited_by_count":97},{"id":"2406.09136","title":"Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs","created":"2024-06-13","cited_by_count":96},{"id":"2311.18232","title":"LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models","created":"2023-11-30","cited_by_count":88},{"id":"1912.02503","title":"Hindsight Credit Assignment","created":"2019-12-05","cited_by_count":79},{"id":"2306.08189","title":"Language models are not naysayers: An analysis of language models on negation benchmarks","created":"2023-06-14","cited_by_count":74},{"id":"2404.05221","title":"LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models","created":"2024-04-08","cited_by_count":70},{"id":"2405.14655","title":"Multi-turn Reinforcement Learning from Preference Human Feedback","created":"2024-05-23","cited_by_count":67},{"id":"2304.07297","title":"Language Instructed Reinforcement Learning for Human-AI Coordination","created":"2023-04-13","cited_by_count":63},{"id":"2501.09620","title":"Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment","created":"2025-01-16","cited_by_count":42},{"id":"2312.01350","title":"Honesty Is the Best Policy: Defining and Mitigating AI Deception","created":"2023-12-03","cited_by_count":40},{"id":"1909.02128","title":"No Press Diplomacy: Modeling Multi-Agent Gameplay","created":"2019-09-04","cited_by_count":38},{"id":"1810.05903","title":"Towards Formal Definitions of Blameworthiness, Intention, and Moral Responsibility","created":"2018-10-13","cited_by_count":32},{"id":"2104.02871","title":"On the Critical Role of Conventions in Adaptive Human-AI Collaboration","created":"2021-04-07","cited_by_count":27},{"id":"2108.05271","title":"DeliData: A dataset for deliberation in multi-party problem solving","created":"2021-08-11","cited_by_count":26},{"id":"2310.02168","title":"Editing Personality for Large Language Models","created":"2023-10-03","cited_by_count":22},{"id":"2204.10018","title":"Path-Specific Objectives for Safer Agent Incentives","created":"2022-04-21","cited_by_count":20},{"id":"2401.14215","title":"Commonsense-augmented Memory Construction and Management in Long-term Conversations via Context-aware Persona Refinement","created":"2024-01-25","cited_by_count":14},{"id":"2403.17284","title":"Common Ground Tracking in Multimodal Dialogue","created":"2024-03-26","cited_by_count":13},{"id":"2102.07716","title":"How RL Agents Behave When Their Actions Are Modified","created":"2021-02-15","cited_by_count":10},{"id":"2503.09511","title":"TRACE: Real-Time Multimodal Common Ground Tracking in Situated Collaborative Dialogues","created":"2025-03-12","cited_by_count":9},{"id":"2409.11917","title":"LLMs in Education: Novel Perspectives, Challenges, and Opportunities","created":"2024-09-18","cited_by_count":7},{"id":"2205.12880","title":"Trust-based Consensus in Multi-Agent Reinforcement Learning Systems","created":"2022-05-25","cited_by_count":6},{"id":"2410.19301","title":"Any Other Thoughts, Hedgehog? Linking Deliberation Chains in Collaborative Dialogues","created":"2024-10-25","cited_by_count":6},{"id":"2401.04934","title":"Fully Decentralized Cooperative Multi-Agent Reinforcement Learning: A Survey","created":"2024-01-10","cited_by_count":5},{"id":"2506.10934","title":"Dynamic Epistemic Friction in Dialogue","created":"2025-06-12","cited_by_count":4},{"id":"2502.07717","title":"Making Language Models Robust Against Negation","created":"2025-02-11","cited_by_count":3},{"id":"2504.04815","title":"Beyond Answers: How LLMs Can Pursue Strategic Thinking in Education","created":"2025-04-07","cited_by_count":2},{"id":"2402.01427","title":"The effect of diversity on group decision-making","created":"2024-02-02","cited_by_count":1},{"id":"2510.01432","title":"On the Role of Domain Experts in Creating Effective Tutoring Systems","created":"2025-10-01","cited_by_count":1}],"next_cursor":null}