{"list":"other","total":95,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"2305.19118","title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate","created":"2023-05-30","cited_by_count":1011},{"id":"2307.07924","title":"ChatDev: Communicative Agents for Software Development","created":"2023-07-16","cited_by_count":919},{"id":"2305.14233","title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","created":"2023-05-23","cited_by_count":839},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"id":"1702.01135","title":"Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks","created":"2017-02-03","cited_by_count":744},{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686},{"id":"2401.10020","title":"Self-Rewarding Language Models","created":"2024-01-18","cited_by_count":681},{"id":"2210.11610","title":"Large Language Models Can Self-Improve","created":"2022-10-20","cited_by_count":664},{"id":"2309.00267","title":"RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback","created":"2023-09-01","cited_by_count":625},{"id":"2309.16797","title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","created":"2023-09-28","cited_by_count":551},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467},{"id":"2407.12784","title":"AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases","created":"2024-07-17","cited_by_count":429},{"id":"1805.00899","title":"AI safety via debate","created":"2018-05-02","cited_by_count":400},{"id":"2307.01928","title":"Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners","created":"2023-07-04","cited_by_count":308},{"id":"2305.19187","title":"Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models","created":"2023-05-30","cited_by_count":293},{"id":"2301.11270","title":"Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons","created":"2023-01-26","cited_by_count":247},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243},{"id":"2308.03188","title":"Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies","created":"2023-08-06","cited_by_count":238},{"id":"2310.07579","title":"In-Context Unlearning: Language Models as Few Shot Unlearners","created":"2023-10-11","cited_by_count":224},{"id":"2310.02124","title":"Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View","created":"2023-10-03","cited_by_count":222},{"id":"2407.19594","title":"Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge","created":"2024-07-28","cited_by_count":204},{"id":"2404.02078","title":"Advancing LLM Reasoning Generalists with Preference Trees","created":"2024-04-02","cited_by_count":192},{"id":"2402.00888","title":"Security and Privacy Challenges of Large Language Models: A Survey","created":"2024-01-30","cited_by_count":186},{"id":"2502.08691","title":"AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society","created":"2025-02-12","cited_by_count":186},{"id":"2309.13788","title":"Can LLM-Generated Misinformation Be Detected?","created":"2023-09-25","cited_by_count":177},{"id":"2307.01379","title":"Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models","created":"2023-07-03","cited_by_count":150},{"id":"1810.08575","title":"Supervising strong learners by amplifying weak experts","created":"2018-10-19","cited_by_count":145},{"id":"2311.01043","title":"LLM4Drive: A Survey of Large Language Models for Autonomous Driving","created":"2023-11-02","cited_by_count":136},{"id":"1811.00741","title":"Stronger Data Poisoning Attacks Break Data Sanitization Defenses","created":"2018-11-02","cited_by_count":135},{"id":"2412.05563","title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","created":"2024-12-07","cited_by_count":121},{"id":"2110.06674","title":"Truthful AI: Developing and governing AI that does not lie","created":"2021-10-13","cited_by_count":113},{"id":"2402.07510","title":"Secret Collusion among AI Agents: Multi-Agent Deception via Steganography","created":"2024-02-12","cited_by_count":113},{"id":"2312.09085","title":"The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation","created":"2023-12-14","cited_by_count":109},{"id":"2402.19085","title":"Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment","created":"2024-02-29","cited_by_count":107},{"id":"2010.03522","title":"A Survey of Deep Meta-Learning","created":"2020-10-07","cited_by_count":100},{"id":"2409.05556","title":"SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning","created":"2024-09-09","cited_by_count":94},{"id":"2305.11391","title":"A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation","created":"2023-05-19","cited_by_count":93},{"id":"2407.07791","title":"Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communities","created":"2024-07-10","cited_by_count":86},{"id":"2403.20279","title":"LUQ: Long-text Uncertainty Quantification for LLMs","created":"2024-03-29","cited_by_count":81},{"id":"2406.02622","title":"Safeguarding Large Language Models: A Survey","created":"2024-06-03","cited_by_count":78},{"id":"2408.13006","title":"Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templates","created":"2024-08-23","cited_by_count":72},{"id":"2404.15269","title":"Aligning LLM Agents by Learning Latent Preference from User Edits","created":"2024-04-23","cited_by_count":69},{"id":"2311.08562","title":"MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration","created":"2023-11-14","cited_by_count":57},{"id":"2311.14125","title":"Scalable AI Safety via Doubly-Efficient Debate","created":"2023-11-23","cited_by_count":57},{"id":"2305.00955","title":"Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation","created":"2023-05-01","cited_by_count":55},{"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},{"id":"2307.04986","title":"Epidemic Modeling with Generative Agents","created":"2023-07-11","cited_by_count":49},{"id":"2402.12327","title":"Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents","created":"2024-02-19","cited_by_count":48},{"id":"2312.15523","title":"The Persuasive Power of Large Language Models","created":"2023-12-24","cited_by_count":47},{"id":"2410.12855","title":"JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework","created":"2024-10-11","cited_by_count":47},{"id":"2010.11926","title":"Neural-Symbolic Integration: A Compositional Perspective","created":"2020-10-22","cited_by_count":45},{"id":"2402.01135","title":"A Multi-Agent Conversational Recommender System","created":"2024-02-02","cited_by_count":43},{"id":"2106.06137","title":"Conformal Bayesian Computation","created":"2021-06-11","cited_by_count":39},{"id":"2410.01639","title":"Moral Alignment for LLM Agents","created":"2024-10-02","cited_by_count":39},{"id":"2405.14744","title":"Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View","created":"2024-05-23","cited_by_count":38},{"id":"2310.09139","title":"The Consensus Game: Language Model Generation via Equilibrium Search","created":"2023-10-13","cited_by_count":36},{"id":"2402.16499","title":"LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments","created":"2024-02-26","cited_by_count":36},{"id":"2307.06187","title":"Self-Adaptive Large Language Model (LLM)-Based Multiagent Systems","created":"2023-07-12","cited_by_count":31},{"id":"2310.04782","title":"Improving the Reliability of Large Language Models by Leveraging Uncertainty-Aware In-Context Learning","created":"2023-10-07","cited_by_count":29},{"id":"2410.00031","title":"Strategic Collusion of LLM Agents: Market Division in Multi-Commodity Competitions","created":"2024-09-19","cited_by_count":26},{"id":"2308.03313","title":"Quantifying the Impact of Large Language Models on Collective Opinion Dynamics","created":"2023-08-07","cited_by_count":22},{"id":"2402.11398","title":"Reasoning before Comparison: LLM-Enhanced Semantic Similarity Metrics for Domain Specialized Text Analysis","created":"2024-02-17","cited_by_count":21},{"id":"2406.15567","title":"SAIL: Self-Improving Efficient Online Alignment of Large Language Models","created":"2024-06-21","cited_by_count":20},{"id":"2402.18150","title":"Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation","created":"2024-02-28","cited_by_count":19},{"id":"2404.14313","title":"Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels","created":"2024-04-22","cited_by_count":19},{"id":"2402.15368","title":"Probabilistically Correct Language-based Multi-Robot Planning using Conformal Prediction","created":"2024-02-23","cited_by_count":18},{"id":"2212.10720","title":"MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions","created":"2022-12-21","cited_by_count":17},{"id":"2402.00251","title":"Efficient Non-Parametric Uncertainty Quantification for Black-Box Large Language Models and Decision Planning","created":"2024-02-01","cited_by_count":16},{"id":"2406.00430","title":"Evaluating Uncertainty-based Failure Detection for Closed-Loop LLM Planners","created":"2024-06-01","cited_by_count":15},{"id":"2410.15168","title":"An Electoral Approach to Diversify LLM-based Multi-Agent Collective Decision-Making","created":"2024-10-19","cited_by_count":14},{"id":"2407.11282","title":"Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models","created":"2024-07-15","cited_by_count":13},{"id":"2409.07085","title":"Understanding Knowledge Drift in LLMs through Misinformation","created":"2024-09-11","cited_by_count":10},{"id":"2010.00330","title":"Workflow Provenance in the Lifecycle of Scientific Machine Learning","created":"2020-09-30","cited_by_count":9},{"id":"2105.01850","title":"Preference learning along multiple criteria: A game-theoretic perspective","created":"2021-05-05","cited_by_count":9},{"id":"2411.05348","title":"LLM-PySC2: Starcraft II learning environment for Large Language Models","created":"2024-11-08","cited_by_count":9},{"id":"2508.11425","title":"Tapas Are Free! Training-Free Adaptation of Programmatic Agents via LLM-Guided Program Synthesis in Dynamic Environments","created":"2025-08-15","cited_by_count":9},{"id":"2408.08959","title":"Trust-Oriented Adaptive Guardrails for Large Language Models","created":"2024-08-16","cited_by_count":8},{"id":"2205.12880","title":"Trust-based Consensus in Multi-Agent Reinforcement Learning Systems","created":"2022-05-25","cited_by_count":6},{"id":"2307.11784","title":"What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety Critical Systems","created":"2023-07-20","cited_by_count":6},{"id":"2507.04100","title":"Hierarchical Testing with Rabbit Optimization for Industrial Cyber-Physical Systems","created":"2025-07-05","cited_by_count":4},{"id":"2503.10872","title":"TAIJI: Textual Anchoring for Immunizing Jailbreak Images in Vision Language Models","created":"2025-03-13","cited_by_count":3},{"id":"2207.05678","title":"Symbolic Runtime Verification for Monitoring under Uncertainties and Assumptions","created":"2022-07-12","cited_by_count":2}],"next_cursor":null}