{"total":193,"rows":[{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499,"area":"alignment"},{"id":"2406.05946","title":"Safety Alignment Should Be Made More Than Just a Few Tokens Deep","created":"2024-06-10","cited_by_count":472,"area":"alignment"},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467,"area":"alignment"},{"id":"2310.01377","title":"UltraFeedback: Boosting Language Models with Scaled AI Feedback","created":"2023-10-02","cited_by_count":406,"area":"alignment"},{"id":"2410.16184","title":"RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style","created":"2024-10-21","cited_by_count":176,"area":"alignment"},{"id":"2309.11489","title":"Text2Reward: Reward Shaping with Language Models for Reinforcement Learning","created":"2023-09-20","cited_by_count":160,"area":"alignment"},{"id":"2506.01937","title":"RewardBench 2: Advancing Reward Model Evaluation","created":"2025-06-02","cited_by_count":150,"area":"alignment"},{"id":"2310.03708","title":"Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization","created":"2023-10-05","cited_by_count":124,"area":"alignment"},{"id":"2405.21046","title":"Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF","created":"2024-05-31","cited_by_count":106,"area":"alignment"},{"id":"2402.02416","title":"Aligner: Efficient Alignment by Learning to Correct","created":"2024-02-04","cited_by_count":98,"area":"alignment"},{"id":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96,"area":"alignment"},{"id":"2410.14872","title":"How to Evaluate Reward Models for RLHF","created":"2024-10-18","cited_by_count":88,"area":"alignment"},{"id":"2506.11902","title":"TreeRL: LLM Reinforcement Learning with On-Policy Tree Search","created":"2025-06-13","cited_by_count":80,"area":"alignment"},{"id":"2407.14622","title":"BOND: Aligning LLMs with Best-of-N Distillation","created":"2024-07-19","cited_by_count":76,"area":"alignment"},{"id":"2302.05206","title":"The Wisdom of Hindsight Makes Language Models Better Instruction Followers","created":"2023-02-10","cited_by_count":62,"area":"alignment"},{"id":"2507.08794","title":"One Token to Fool LLM-as-a-Judge","created":"2025-07-11","cited_by_count":60,"area":"alignment"},{"id":"2404.09656","title":"Learn Your Reference Model for Real Good Alignment","created":"2024-04-15","cited_by_count":57,"area":"alignment"},{"id":"2310.05910","title":"SALMON: Self-Alignment with Instructable Reward Models","created":"2023-10-09","cited_by_count":55,"area":"alignment"},{"id":"2308.00225","title":"Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive Bias","created":"2023-08-01","cited_by_count":53,"area":"alignment"},{"id":"2602.02482","title":"Expanding the Capabilities of Reinforcement Learning via Text Feedback","created":"2026-02-02","cited_by_count":53,"area":"alignment"},{"id":"2412.14516","title":"Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment","created":"2024-12-19","cited_by_count":51,"area":"alignment"},{"id":"2408.06266","title":"Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment","created":"2024-08-12","cited_by_count":46,"area":"alignment"},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"area":"alignment"},{"id":"2409.20370","title":"The Perfect Blend: Redefining RLHF with Mixture of Judges","created":"2024-09-30","cited_by_count":43,"area":"alignment"},{"id":"2507.00769","title":"LitBench: A Benchmark and Dataset for Reliable Evaluation of Creative Writing","created":"2025-07-01","cited_by_count":42,"area":"alignment"},{"id":"2508.03686","title":"CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward","created":"2025-08-05","cited_by_count":40,"area":"alignment"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2409.15268","title":"Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking","created":"2024-09-23","cited_by_count":35,"area":"alignment"},{"id":"2506.19248","title":"Inference-Time Reward Hacking in Large Language Models","created":"2025-06-24","cited_by_count":34,"area":"alignment"},{"id":"2506.23235","title":"Generalist Reward Models: Found Inside Large Language Models","created":"2025-06-29","cited_by_count":34,"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":"2504.19599","title":"GVPO: Group Variance Policy Optimization for Large Language Model Post-Training","created":"2025-04-28","cited_by_count":32,"area":"alignment"},{"id":"2509.03403","title":"Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training","created":"2025-09-03","cited_by_count":29,"area":"alignment"},{"id":"2502.00883","title":"SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters","created":"2025-02-02","cited_by_count":25,"area":"alignment"},{"id":"2511.08594","title":"Diverse Preference Learning for Capabilities and Alignment","created":"2025-10-29","cited_by_count":25,"area":"alignment"},{"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":"2507.18631","title":"Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment","created":"2025-07-24","cited_by_count":24,"area":"alignment"},{"id":"2412.06000","title":"Does RLHF Scale? Exploring the Impacts From Data, Model, and Method","created":"2024-12-08","cited_by_count":23,"area":"alignment"},{"id":"2509.11452","title":"Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting","created":"2025-09-14","cited_by_count":23,"area":"alignment"},{"id":"2502.07460","title":"Logarithmic Regret for Online KL-Regularized Reinforcement Learning","created":"2025-02-11","cited_by_count":22,"area":"alignment"},{"id":"2504.04950","title":"A Unified Pairwise Framework for RLHF: Bridging Generative Reward Modeling and Policy Optimization","created":"2025-04-07","cited_by_count":21,"area":"alignment"},{"id":"2412.11041","title":"Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models","created":"2024-12-15","cited_by_count":20,"area":"alignment"},{"id":"2503.18991","title":"Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment","created":"2025-03-23","cited_by_count":20,"area":"alignment"},{"id":"2501.12273","title":"Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement","created":"2025-01-21","cited_by_count":18,"area":"alignment"},{"id":"2405.13820","title":"Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching","created":"2024-05-22","cited_by_count":17,"area":"alignment"},{"id":"2402.12219","title":"Reformatted Alignment","created":"2024-02-19","cited_by_count":15,"area":"alignment"},{"id":"2607.15161","title":"On-Policy Delta Distillation","created":"2026-07-16","cited_by_count":15,"area":"alignment"},{"id":"2409.02231","title":"SmileyLlama: Modifying Large Language Models for Directed Chemical Space Exploration","created":"2024-09-03","cited_by_count":14,"area":"alignment"},{"id":"2505.19653","title":"Token-Importance Guided Direct Preference Optimization","created":"2025-05-26","cited_by_count":14,"area":"alignment"},{"id":"2506.14681","title":"Massive Supervised Fine-tuning Experiments Reveal How Data, Layer, and Training Factors Shape LLM Alignment Quality","created":"2025-06-17","cited_by_count":14,"area":"alignment"},{"id":"2510.01555","title":"Rethinking KL Regularization in RLHF: From Value Estimation to Gradient Optimization","created":"2025-10-02","cited_by_count":14,"area":"alignment"},{"id":"2510.26374","title":"BOTS: A Unified Framework for Bayesian Online Task Selection in LLM Reinforcement Finetuning","created":"2025-10-30","cited_by_count":14,"area":"alignment"},{"id":"2503.05079","title":"On a Connection Between Imitation Learning and RLHF","created":"2025-03-07","cited_by_count":13,"area":"alignment"},{"id":"2505.07437","title":"LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning","created":"2025-05-12","cited_by_count":13,"area":"alignment"},{"id":"2505.10527","title":"WorldPM: Scaling Human Preference Modeling","created":"2025-05-15","cited_by_count":13,"area":"alignment"},{"id":"2412.01253","title":"Yi-Lightning Technical Report","created":"2024-12-02","cited_by_count":12,"area":"alignment"},{"id":"2506.20495","title":"ReCode: Updating Code API Knowledge with Reinforcement Learning","created":"2025-06-25","cited_by_count":12,"area":"alignment"},{"id":"2505.12763","title":"Rethinking Reward Model Evaluation Through the Lens of Reward Overoptimization","created":"2025-05-19","cited_by_count":11,"area":"alignment"},{"id":"2512.11391","title":"Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization","created":"2025-12-12","cited_by_count":11,"area":"alignment"},{"id":"2601.07349","title":"Reward Modeling from Natural Language Human Feedback","created":"2026-01-12","cited_by_count":11,"area":"alignment"},{"id":"2311.05821","title":"Let's Reinforce Step by Step","created":"2023-11-10","cited_by_count":10,"area":"alignment"},{"id":"2505.11166","title":"SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization","created":"2025-05-16","cited_by_count":10,"area":"alignment"},{"id":"2510.17426","title":"Navigating the Alignment-Calibration Trade-off: A Pareto-Superior Frontier via Model Merging","created":"2025-10-20","cited_by_count":10,"area":"alignment"},{"id":"2410.05102","title":"SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks","created":"2024-10-07","cited_by_count":9,"area":"alignment"},{"id":"2505.12225","title":"Mining Intrinsic Rewards from LLM Hidden States for Efficient Best-of-N Sampling","created":"2025-05-18","cited_by_count":9,"area":"alignment"},{"id":"2311.07723","title":"Generalization Analogies: A Testbed for Generalizing AI Oversight to Hard-To-Measure Domains","created":"2023-11-13","cited_by_count":8,"area":"alignment"},{"id":"2403.14238","title":"Reinforcement Learning from Reflective Feedback (RLRF): Aligning and Improving LLMs via Fine-Grained Self-Reflection","created":"2024-03-21","cited_by_count":8,"area":"alignment"},{"id":"2405.18718","title":"Efficient Model-agnostic Alignment via Bayesian Persuasion","created":"2024-05-29","cited_by_count":8,"area":"alignment"},{"id":"2505.12762","title":"IDEAL: Data Equilibrium Adaptation for Multi-Capability Language Model Alignment","created":"2025-05-19","cited_by_count":8,"area":"alignment"},{"id":"2505.13878","title":"InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models","created":"2025-05-20","cited_by_count":8,"area":"alignment"},{"id":"2507.11500","title":"ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning","created":"2025-07-14","cited_by_count":8,"area":"alignment"},{"id":"2509.15110","title":"TDRM: Smooth Reward Models with Temporal Difference for LLM RL and Inference","created":"2025-09-18","cited_by_count":8,"area":"alignment"},{"id":"2509.23873","title":"Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning","created":"2025-09-28","cited_by_count":8,"area":"alignment"},{"id":"2602.18037","title":"Gradient Regularization Mitigates Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards","created":"2026-02-20","cited_by_count":8,"area":"alignment"},{"id":"2406.12606","title":"Not Everything is All You Need: Toward Low-Redundant Optimization for Large Language Model Alignment","created":"2024-06-18","cited_by_count":7,"area":"alignment"},{"id":"2407.06542","title":"LIONs: An Empirically Optimized Approach to Align Language Models","created":"2024-07-09","cited_by_count":7,"area":"alignment"},{"id":"2408.07471","title":"Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization","created":"2024-08-14","cited_by_count":7,"area":"alignment"},{"id":"2410.01735","title":"LASeR: Learning to Adaptively Select Reward Models with Multi-Armed Bandits","created":"2024-10-02","cited_by_count":7,"area":"alignment"},{"id":"2508.14460","title":"DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization","created":"2025-08-20","cited_by_count":7,"area":"alignment"},{"id":"2601.07182","title":"PRPO: Aligning Process Reward with Outcome Reward in Policy Optimization","created":"2026-01-12","cited_by_count":7,"area":"alignment"},{"id":"2408.15339","title":"UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types","created":"2024-08-27","cited_by_count":6,"area":"alignment"},{"id":"2409.11212","title":"Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization","created":"2024-09-17","cited_by_count":6,"area":"alignment"},{"id":"2410.04834","title":"As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss","created":"2024-10-07","cited_by_count":6,"area":"alignment"},{"id":"2410.14940","title":"Baichuan Alignment Technical Report","created":"2024-10-19","cited_by_count":6,"area":"alignment"},{"id":"2502.01925","title":"PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling","created":"2025-02-04","cited_by_count":6,"area":"alignment"},{"id":"2502.14619","title":"Reward Models Identify Consistency, Not Causality","created":"2025-02-20","cited_by_count":6,"area":"alignment"},{"id":"2503.04222","title":"FuseChat-3.0: Preference Optimization Meets Heterogeneous Model Fusion","created":"2025-03-06","cited_by_count":6,"area":"alignment"},{"id":"2505.14185","title":"Safety Subspaces are Not Linearly Distinct: A Fine-Tuning Case Study","created":"2025-05-20","cited_by_count":6,"area":"alignment"},{"id":"2509.18632","title":"A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users","created":"2025-09-23","cited_by_count":6,"area":"alignment"},{"id":"2510.01167","title":"Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards","created":"2025-10-01","cited_by_count":6,"area":"alignment"},{"id":"2601.10589","title":"Be Your Own Red Teamer: Safety Alignment via Self-Play and Reflective Experience Replay","created":"2026-01-15","cited_by_count":6,"area":"alignment"},{"id":"2601.18533","title":"From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation","created":"2026-01-26","cited_by_count":6,"area":"alignment"},{"id":"2602.07892","title":"Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection","created":"2026-02-08","cited_by_count":6,"area":"alignment"},{"id":"2407.01470","title":"DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging","created":"2024-07-01","cited_by_count":5,"area":"alignment"},{"id":"2410.17131","title":"Self-Steering Optimization: Autonomous Preference Optimization for Large Language Models","created":"2024-10-22","cited_by_count":5,"area":"alignment"},{"id":"2502.04602","title":"Extracting and Understanding the Superficial Knowledge in Alignment","created":"2025-02-07","cited_by_count":5,"area":"alignment"},{"id":"2506.22578","title":"The Hidden Link Between RLHF and Contrastive Learning","created":"2025-06-27","cited_by_count":5,"area":"alignment"},{"id":"2507.17515","title":"URPO: A Unified Reward & Policy Optimization Framework for Large Language Models","created":"2025-07-23","cited_by_count":5,"area":"alignment"},{"id":"2509.22099","title":"S2J: Bridging the Gap Between Solving and Judging Ability in Generative Reward Models","created":"2025-09-26","cited_by_count":5,"area":"alignment"},{"id":"2510.08646","title":"Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy","created":"2025-10-09","cited_by_count":5,"area":"alignment"}],"next_cursor":"100"}