{"total":69,"rows":[{"id":"2312.11456","title":"Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint","created":"2023-12-18","cited_by_count":350,"area":"alignment"},{"id":"2404.18922","title":"DPO Meets PPO: Reinforced Token Optimization for RLHF","created":"2024-04-29","cited_by_count":127,"area":"alignment"},{"id":"2402.08925","title":"MaxMin-RLHF: Alignment with Diverse Human Preferences","created":"2024-02-14","cited_by_count":123,"area":"alignment"},{"id":"2405.16436","title":"Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer","created":"2024-05-26","cited_by_count":109,"area":"alignment"},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"area":null},{"id":"2503.21878","title":"Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment","created":"2025-03-27","cited_by_count":97,"area":"alignment"},{"id":"2407.13399","title":"Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization","created":"2024-07-18","cited_by_count":78,"area":"alignment"},{"id":"2402.07314","title":"Online Iterative Reinforcement Learning from Human Feedback with General Preference Model","created":"2024-02-11","cited_by_count":52,"area":"alignment"},{"id":"2404.08495","title":"Dataset Reset Policy Optimization for RLHF","created":"2024-04-12","cited_by_count":41,"area":"alignment"},{"id":"2501.09655","title":"A Survey of Research in Large Language Models for Electronic Design Automation","created":"2025-01-16","cited_by_count":41,"area":null},{"id":"2407.19584","title":"SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain","created":"2024-07-28","cited_by_count":39,"area":null},{"id":"2402.10342","title":"Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization","created":"2024-02-15","cited_by_count":25,"area":"alignment"},{"id":"2403.13219","title":"Diffusion Model for Data-Driven Black-Box Optimization","created":"2024-03-20","cited_by_count":24,"area":"diffusion"},{"id":"2502.07460","title":"Logarithmic Regret for Online KL-Regularized Reinforcement Learning","created":"2025-02-11","cited_by_count":22,"area":"alignment"},{"id":"2402.00854","title":"SymbolicAI: A framework for logic-based approaches combining generative models and solvers","created":"2024-02-01","cited_by_count":16,"area":null},{"id":"2507.06181","title":"CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization","created":"2025-07-08","cited_by_count":16,"area":"lr"},{"id":"2406.04854","title":"Uncertainty Aware Learning for Language Model Alignment","created":"2024-06-07","cited_by_count":13,"area":"alignment"},{"id":"2412.09544","title":"Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking","created":"2024-12-12","cited_by_count":13,"area":"alignment"},{"id":"2404.13752","title":"Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models","created":"2024-04-21","cited_by_count":12,"area":"mechinterp"},{"id":"2409.17401","title":"Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference","created":"2024-09-25","cited_by_count":12,"area":"alignment"},{"id":"2502.11169","title":"CMCTS: A Constrained Monte Carlo Tree Search Framework for Mathematical Reasoning in Large Language Model","created":"2025-02-16","cited_by_count":9,"area":"lr"},{"id":"2504.05181","title":"Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval","created":"2025-04-07","cited_by_count":9,"area":null},{"id":"2505.14585","title":"Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning","created":"2025-05-20","cited_by_count":8,"area":"lr"},{"id":"2310.18628","title":"Personalised Distillation: Empowering Open-Sourced LLMs with Adaptive Learning for Code Generation","created":"2023-10-28","cited_by_count":7,"area":"distill"},{"id":"2505.13403","title":"MR. Judge: Multimodal Reasoner as a Judge","created":"2025-05-19","cited_by_count":7,"area":"lr"},{"id":"2504.13490","title":"Early Timestep Zero-Shot Candidate Selection for Instruction-Guided Image Editing","created":"2025-04-18","cited_by_count":5,"area":"diffusion"},{"id":"2510.06915","title":"LongRM: Revealing and Unlocking the Context Boundary of Reward Modeling","created":"2025-10-08","cited_by_count":5,"area":"alignment"},{"id":"2405.12421","title":"A Unified Linear Programming Framework for Offline Reward Learning from Human Demonstrations and Feedback","created":"2024-05-20","cited_by_count":4,"area":"alignment"},{"id":"2406.03356","title":"Cooperative learning of Pl@ntNet's Artificial Intelligence algorithm: how does it work and how can we improve it?","created":"2024-06-05","cited_by_count":4,"area":null},{"id":"2501.05032","title":"Enhancing Human-Like Responses in Large Language Models","created":"2025-01-09","cited_by_count":4,"area":null},{"id":"2502.05825","title":"Delta -- Contrastive Decoding Mitigates Text Hallucinations in Large Language Models","created":"2025-02-09","cited_by_count":4,"area":null},{"id":"2502.06812","title":"Harness Local Rewards for Global Benefits: Effective Text-to-Video Generation Alignment with Patch-level Reward Models","created":"2025-02-04","cited_by_count":4,"area":"diffusion"},{"id":"2503.05770","title":"Generative Artificial Intelligence: Evolving Technology, Growing Societal Impact, and Opportunities for Information Systems Research","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2503.19201","title":"A Shared Low-Rank Adaptation Approach to Personalized RLHF","created":"2025-03-24","cited_by_count":4,"area":"alignment"},{"id":"2506.03066","title":"Sign-SZPO: Provable Preference-based Reinforcement Learning with an Unknown Link Function","created":"2025-06-03","cited_by_count":4,"area":"deeprl"},{"id":"2311.13053","title":"Beyond Text: Unveiling Multimodal Proficiency of Large Language Models with MultiAPI Benchmark","created":"2023-11-21","cited_by_count":3,"area":null},{"id":"2312.17229","title":"Think Before You Duel: Understanding Complexities of Preference Learning under Constrained Resources","created":"2023-12-28","cited_by_count":3,"area":null},{"id":"2404.12596","title":"Parameter Efficient Diverse Paraphrase Generation Using Sequence-Level Knowledge Distillation","created":"2024-04-19","cited_by_count":3,"area":"distill"},{"id":"2505.01162","title":"On the Limitations of Steering in Language Model Alignment","created":"2025-05-02","cited_by_count":3,"area":"alignment"},{"id":"2509.17866","title":"Understanding Post-Training Structural Changes in Large Language Models","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2510.13022","title":"On the Role of Preference Variance in Preference Optimization","created":"2025-10-14","cited_by_count":3,"area":"alignment"},{"id":"2307.12926","title":"Contextual Bandits and Imitation Learning via Preference-Based Active Queries","created":"2023-07-24","cited_by_count":2,"area":"offlinerl"},{"id":"2403.00528","title":"Large Language Models for Simultaneous Named Entity Extraction and Spelling Correction","created":"2024-03-01","cited_by_count":2,"area":null},{"id":"2509.24245","title":"Prompt and Parameter Co-Optimization for Large Language Models","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2511.12832","title":"From Passive to Persuasive: Localized Activation Injection for Empathy and Negotiation","created":"2025-11-16","cited_by_count":2,"area":"mechinterp"},{"id":"2601.11969","title":"MemoryRewardBench: Benchmarking Reward Models for Long-Term Memory Management in Large Language Models","created":"2026-01-17","cited_by_count":2,"area":"alignment"},{"id":"2602.00603","title":"Direct Preference Optimization with Rating Information: Practical Algorithms and Provable Gains","created":"2026-01-31","cited_by_count":2,"area":"alignment"},{"id":"2403.06267","title":"FARPLS: A Feature-Augmented Robot Trajectory Preference Labeling System to Assist Human Labelers' Preference Elicitation","created":"2024-03-10","cited_by_count":1,"area":null},{"id":"2403.15045","title":"DP-Dueling: Learning from Preference Feedback without Compromising User Privacy","created":"2024-03-22","cited_by_count":1,"area":null},{"id":"2410.11444","title":"A Theoretical Survey on Foundation Models","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2502.08759","title":"Contextual bandits with entropy-based human feedback","created":"2025-02-12","cited_by_count":1,"area":"alignment"},{"id":"2505.07886","title":"PLHF: Prompt Optimization with Few-Shot Human Feedback","created":"2025-05-11","cited_by_count":1,"area":"alignment"},{"id":"2506.01524","title":"V-VAE: A Variational Auto Encoding Framework Towards Fine-Grained Control over Human-Like Chat","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2506.18156","title":"AI Through the Human Lens: Investigating Cognitive Theories in Machine Psychology","created":"2025-06-22","cited_by_count":1,"area":null},{"id":"2604.00200","title":"Offline Constrained RLHF with Multiple Preference Oracles","created":"2026-03-31","cited_by_count":1,"area":"alignment"},{"id":"2607.21013","title":"EmoAgent-R1: Towards Multimodal Emotion Understanding with Reinforcement Learning-based Dynamic Agent Specialization","created":"2026-07-23","cited_by_count":1,"area":"lr"},{"id":"2310.10556","title":"Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks","created":"2023-10-16","cited_by_count":0,"area":"alignment"},{"id":"2402.15703","title":"Is Offline Decision Making Possible with Only Few Samples? Reliable Decisions in Data-Starved Bandits via Trust Region Enhancement","created":"2024-02-24","cited_by_count":0,"area":null},{"id":"2404.00189","title":"GPTA: Generative Prompt Tuning Assistant for Synergistic Downstream Neural Network Enhancement with LLMs","created":"2024-03-29","cited_by_count":0,"area":null},{"id":"2406.19112","title":"A Teacher Is Worth A Million Instructions","created":"2024-06-27","cited_by_count":0,"area":null},{"id":"2505.17413","title":"Conversations: Love Them, Hate Them, Steer Them","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2505.23927","title":"Thompson Sampling in Online RLHF with General Function Approximation","created":"2025-05-29","cited_by_count":0,"area":"alignment"},{"id":"2508.21307","title":"MultiFluxAI Enhancing Platform Engineering with Advanced Agent-Orchestrated Retrieval Systems","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2510.26301","title":"Offline Clustering of Preference Learning with Active-data Augmentation","created":"2025-10-30","cited_by_count":0,"area":"alignment"},{"id":"2601.03436","title":"MARVEL: A Multi Agent-based Research Validator and Enabler using Large Language Models","created":"2026-01-06","cited_by_count":0,"area":"agents"},{"id":"2602.06239","title":"Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution","created":"2026-02-05","cited_by_count":0,"area":"alignment"},{"id":"2603.28281","title":"Corruption-robust Offline Multi-agent Reinforcement Learning From Human Feedback","created":"2026-03-30","cited_by_count":0,"area":"alignment"},{"id":"2605.13155","title":"Pareto-Guided Optimal Transport for Multi-Reward Alignment","created":"2026-05-13","cited_by_count":0,"area":"alignment"},{"id":"2606.01382","title":"Efficient Exploration for Iterative Nash Preference Optimization","created":"2026-05-31","cited_by_count":0,"area":"alignment"}],"next_cursor":null}