{"total":350,"rows":[{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963,"area":"alignment"},{"id":"2406.12845","title":"Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts","created":"2024-06-18","cited_by_count":376,"area":"alignment"},{"id":"2406.08464","title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","created":"2024-06-12","cited_by_count":346,"area":"lr"},{"id":"2405.07863","title":"RLHF Workflow: From Reward Modeling to Online RLHF","created":"2024-05-13","cited_by_count":267,"area":"lr"},{"id":"2404.10719","title":"Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study","created":"2024-04-16","cited_by_count":262,"area":"alignment"},{"id":"2404.14367","title":"Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data","created":"2024-04-22","cited_by_count":185,"area":null},{"id":"2404.03715","title":"Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences","created":"2024-04-04","cited_by_count":178,"area":"alignment"},{"id":"2411.00816","title":"CycleResearcher: Improving Automated Research via Automated Review","created":"2024-10-28","cited_by_count":148,"area":null},{"id":"2504.11343","title":"A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce","created":"2025-04-15","cited_by_count":145,"area":"lr"},{"id":"2404.18922","title":"DPO Meets PPO: Reinforced Token Optimization for RLHF","created":"2024-04-29","cited_by_count":127,"area":"alignment"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2406.00832","title":"BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling","created":"2024-06-02","cited_by_count":121,"area":"alignment"},{"id":"2407.10457","title":"The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism","created":"2024-07-15","cited_by_count":116,"area":null},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2405.20304","title":"Group Robust Preference Optimization in Reward-free RLHF","created":"2024-05-30","cited_by_count":95,"area":"lr"},{"id":"2407.10490","title":"Learning Dynamics of LLM Finetuning","created":"2024-07-15","cited_by_count":95,"area":"alignment"},{"id":"2406.18853","title":"Decoding-Time Language Model Alignment with Multiple Objectives","created":"2024-06-27","cited_by_count":94,"area":"alignment"},{"id":"2407.06551","title":"OffsetBias: Leveraging Debiased Data for Tuning Evaluators","created":"2024-07-09","cited_by_count":94,"area":null},{"id":"2509.06941","title":"Outcome-based Exploration for LLM Reasoning","created":"2025-09-08","cited_by_count":83,"area":"lr"},{"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":"2409.13156","title":"RRM: Robust Reward Model Training Mitigates Reward Hacking","created":"2024-09-20","cited_by_count":76,"area":"alignment"},{"id":"2403.08730","title":"Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization","created":"2024-03-13","cited_by_count":75,"area":"mllm"},{"id":"2410.00847","title":"Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown","created":"2024-10-01","cited_by_count":74,"area":"alignment"},{"id":"2405.16455","title":"On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization","created":"2024-05-26","cited_by_count":72,"area":"alignment"},{"id":"2412.10400","title":"Reinforcement Learning Enhanced LLMs: A Survey","created":"2024-12-05","cited_by_count":71,"area":"lr"},{"id":"2502.19613","title":"Self-rewarding correction for mathematical reasoning","created":"2025-02-26","cited_by_count":70,"area":"lr"},{"id":"2404.16767","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","created":"2024-04-25","cited_by_count":69,"area":"alignment"},{"id":"2405.19316","title":"Robust Preference Optimization through Reward Model Distillation","created":"2024-05-29","cited_by_count":67,"area":"alignment"},{"id":"2410.08847","title":"Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization","created":"2024-10-11","cited_by_count":67,"area":"alignment"},{"id":"2409.02392","title":"Building Math Agents with Multi-Turn Iterative Preference Learning","created":"2024-09-04","cited_by_count":66,"area":"lr"},{"id":"2410.03642","title":"Aligning LLMs with Individual Preferences via Interaction","created":"2024-10-04","cited_by_count":63,"area":"alignment"},{"id":"2410.16033","title":"TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling","created":"2024-10-18","cited_by_count":61,"area":"lr"},{"id":"2406.01462","title":"The Importance of Online Data: Understanding Preference Fine-tuning via Coverage","created":"2024-06-03","cited_by_count":55,"area":"alignment"},{"id":"2412.16145","title":"Offline Reinforcement Learning for LLM Multi-Step Reasoning","created":"2024-12-20","cited_by_count":54,"area":"lr"},{"id":"2602.01511","title":"Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training","created":"2026-02-02","cited_by_count":54,"area":"alignment"},{"id":"2406.06144","title":"Language Models Resist Alignment: Evidence From Data Compression","created":"2024-06-10","cited_by_count":53,"area":null},{"id":"2406.09760","title":"Bootstrapping Language Models with DPO Implicit Rewards","created":"2024-06-14","cited_by_count":53,"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":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52,"area":null},{"id":"2505.20347","title":"SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data","created":"2025-05-25","cited_by_count":51,"area":"lr"},{"id":"2409.11704","title":"From Lists to Emojis: How Format Bias Affects Model Alignment","created":"2024-09-18","cited_by_count":49,"area":"alignment"},{"id":"2505.11711","title":"Reinforcement Learning Finetunes Small Subnetworks in Large Language Models","created":"2025-05-16","cited_by_count":49,"area":null},{"id":"2504.13139","title":"Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo","created":"2025-04-17","cited_by_count":46,"area":null},{"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,"area":"alignment"},{"id":"2511.07919","title":"Feedback Descent: Open-Ended Text Optimization via Pairwise Comparison","created":"2025-11-11","cited_by_count":44,"area":"alignment"},{"id":"2406.16306","title":"Cascade Reward Sampling for Efficient Decoding-Time Alignment","created":"2024-06-24","cited_by_count":39,"area":"alignment"},{"id":"2509.17940","title":"DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving","created":"2025-09-22","cited_by_count":39,"area":"driving"},{"id":"2412.11006","title":"Entropy-Regularized Process Reward Model","created":"2024-12-15","cited_by_count":38,"area":"lr"},{"id":"2505.18116","title":"NFT: Bridging Supervised Learning and Reinforcement Learning in Math Reasoning","created":"2025-05-23","cited_by_count":38,"area":"lr"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2409.07253","title":"Alignment of Diffusion Models: Fundamentals, Challenges, and Future","created":"2024-09-11","cited_by_count":35,"area":"diffusion"},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2403.05171","title":"Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation","created":"2024-03-08","cited_by_count":33,"area":"alignment"},{"id":"2411.04625","title":"Sharp Analysis for KL-Regularized Contextual Bandits and RLHF","created":"2024-11-07","cited_by_count":33,"area":"alignment"},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33,"area":"alignment"},{"id":"2409.11239","title":"LLM-as-a-Judge & Reward Model: What They Can and Cannot Do","created":"2024-09-17","cited_by_count":32,"area":"alignment"},{"id":"2410.03742","title":"Beyond Scalar Reward Model: Learning Generative Judge from Preference Data","created":"2024-10-01","cited_by_count":32,"area":"alignment"},{"id":"2505.20075","title":"Curriculum-RLAIF: Curriculum Alignment with Reinforcement Learning from AI Feedback","created":"2025-05-26","cited_by_count":32,"area":"alignment"},{"id":"2408.15549","title":"WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback","created":"2024-08-28","cited_by_count":31,"area":"alignment"},{"id":"2409.11365","title":"CoCA: Regaining Safety-awareness of Multimodal Large Language Models with Constitutional Calibration","created":"2024-09-17","cited_by_count":31,"area":"mllm"},{"id":"2404.11049","title":"Stepwise Alignment for Constrained Language Model Policy Optimization","created":"2024-04-17","cited_by_count":30,"area":"alignment"},{"id":"2410.04612","title":"Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF","created":"2024-10-06","cited_by_count":30,"area":"alignment"},{"id":"2502.01042","title":"SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals","created":"2025-02-03","cited_by_count":29,"area":"safety"},{"id":"2503.18929","title":"Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training","created":"2025-03-24","cited_by_count":29,"area":"lr"},{"id":"2506.20520","title":"Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards","created":"2025-06-25","cited_by_count":29,"area":"lr"},{"id":"2403.01857","title":"Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences","created":"2024-03-04","cited_by_count":27,"area":"alignment"},{"id":"2406.04412","title":"Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment","created":"2024-06-06","cited_by_count":27,"area":"alignment"},{"id":"2409.03650","title":"On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization","created":"2024-09-05","cited_by_count":27,"area":"alignment"},{"id":"2409.19605","title":"The Crucial Role of Samplers in Online Direct Preference Optimization","created":"2024-09-29","cited_by_count":27,"area":"alignment"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2506.08379","title":"Reinforce LLM Reasoning through Multi-Agent Reflection","created":"2025-06-10","cited_by_count":27,"area":"lr"},{"id":"2512.16912","title":"Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward","created":"2025-12-18","cited_by_count":27,"area":"lr"},{"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":"2405.19673","title":"Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models","created":"2024-05-30","cited_by_count":25,"area":"diffusion"},{"id":"2408.13518","title":"Selective Preference Optimization via Token-Level Reward Function Estimation","created":"2024-08-24","cited_by_count":25,"area":"lr"},{"id":"2506.21495","title":"Bridging Offline and Online Reinforcement Learning for LLMs","created":"2025-06-26","cited_by_count":25,"area":null},{"id":"2510.04996","title":"Reinforce-Ada: An Adaptive Sampling Framework under Non-linear RL Objectives","created":"2025-10-06","cited_by_count":25,"area":"lr"},{"id":"2406.07327","title":"3D-Properties: Identifying Challenges in DPO and Charting a Path Forward","created":"2024-06-11","cited_by_count":24,"area":"alignment"},{"id":"2502.16852","title":"Improving LLM General Preference Alignment via Optimistic Online Mirror Descent","created":"2025-02-24","cited_by_count":24,"area":"alignment"},{"id":"2406.11817","title":"Iterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4 Level","created":"2024-06-17","cited_by_count":22,"area":"alignment"},{"id":"2407.14916","title":"Improving Context-Aware Preference Modeling for Language Models","created":"2024-07-20","cited_by_count":22,"area":"alignment"},{"id":"2410.07672","title":"MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization","created":"2024-10-10","cited_by_count":22,"area":"agents"},{"id":"2410.09302","title":"Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization","created":"2024-10-11","cited_by_count":22,"area":"lr"},{"id":"2502.07460","title":"Logarithmic Regret for Online KL-Regularized Reinforcement Learning","created":"2025-02-11","cited_by_count":22,"area":"alignment"},{"id":"2409.09603","title":"Towards Data-Centric RLHF: Simple Metrics for Preference Dataset Comparison","created":"2024-09-15","cited_by_count":21,"area":"alignment"},{"id":"2411.00062","title":"Scalable Reinforcement Post-Training Beyond Static Human Prompts: Evolving Alignment via Asymmetric Self-Play","created":"2024-10-31","cited_by_count":21,"area":"alignment"},{"id":"2502.12858","title":"Rejected Dialects: Biases Against African American Language in Reward Models","created":"2025-02-18","cited_by_count":20,"area":"alignment"},{"id":"2502.18934","title":"Kanana: Compute-efficient Bilingual Language Models","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2602.03143","title":"Self-Hinting Language Models Enhance Reinforcement Learning","created":"2026-02-03","cited_by_count":20,"area":"lr"},{"id":"2409.17819","title":"Inference-Time Language Model Alignment via Integrated Value Guidance","created":"2024-09-26","cited_by_count":19,"area":"alignment"},{"id":"2410.03837","title":"Learning Code Preference via Synthetic Evolution","created":"2024-10-04","cited_by_count":19,"area":null},{"id":"2410.04203","title":"RainbowPO: A Unified Framework for Combining Improvements in Preference Optimization","created":"2024-10-05","cited_by_count":19,"area":"alignment"},{"id":"2505.11595","title":"Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO","created":"2025-05-16","cited_by_count":19,"area":"lr"},{"id":"2507.23158","title":"User Feedback in Human-LLM Dialogues: A Lens to Understand Users But Noisy as a Learning Signal","created":"2025-07-30","cited_by_count":19,"area":null},{"id":"2411.11072","title":"Multilingual Large Language Models: A Systematic Survey","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2506.06923","title":"Boosting LLM Reasoning via Spontaneous Self-Correction","created":"2025-06-07","cited_by_count":18,"area":"lr"},{"id":"2404.04286","title":"Bias Amplification in Language Model Evolution: An Iterated Learning Perspective","created":"2024-04-04","cited_by_count":17,"area":null},{"id":"2502.10581","title":"Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective","created":"2025-02-14","cited_by_count":17,"area":"lr"},{"id":"2506.17252","title":"Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization","created":"2025-06-08","cited_by_count":17,"area":"alignment"},{"id":"2404.04102","title":"ROPO: Robust Preference Optimization for Large Language Models","created":"2024-04-05","cited_by_count":16,"area":"alignment"}],"next_cursor":"100"}