{"total":60,"rows":[{"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":"2506.01937","title":"RewardBench 2: Advancing Reward Model Evaluation","created":"2025-06-02","cited_by_count":150,"area":"alignment"},{"id":"2510.07743","title":"OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment","created":"2025-10-09","cited_by_count":132,"area":"alignment"},{"id":"2410.15522","title":"M-RewardBench: Evaluating Reward Models in Multilingual Settings","created":"2024-10-20","cited_by_count":50,"area":"alignment"},{"id":"2502.12668","title":"Evaluation of Best-of-N Sampling Strategies for Language Model Alignment","created":"2025-02-18","cited_by_count":39,"area":"alignment"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2410.17578","title":"MM-Eval: A Multilingual Meta-Evaluation Benchmark for LLM-as-a-Judge and Reward Models","created":"2024-10-23","cited_by_count":35,"area":"alignment"},{"id":"2410.19133","title":"Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback","created":"2024-10-24","cited_by_count":26,"area":"alignment"},{"id":"2510.26202","title":"What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data","created":"2025-10-30","cited_by_count":26,"area":"alignment"},{"id":"2407.06443","title":"Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment","created":"2024-07-08","cited_by_count":25,"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":"2409.06957","title":"Policy Filtration for RLHF to Mitigate Noise in Reward Models","created":"2024-09-11","cited_by_count":22,"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":"2501.18532","title":"Differentially Private Steering for Large Language Model Alignment","created":"2025-01-30","cited_by_count":15,"area":"alignment"},{"id":"2506.12725","title":"Rethinking DPO: The Role of Rejected Responses in Preference Misalignment","created":"2025-06-15","cited_by_count":15,"area":"alignment"},{"id":"2505.10527","title":"WorldPM: Scaling Human Preference Modeling","created":"2025-05-15","cited_by_count":13,"area":"alignment"},{"id":"2510.20369","title":"Ask a Strong LLM Judge when Your Reward Model is Uncertain","created":"2025-10-23","cited_by_count":13,"area":"alignment"},{"id":"2508.18312","title":"What Matters in Data for DPO?","created":"2025-08-23","cited_by_count":12,"area":"alignment"},{"id":"2603.08035","title":"CDRRM: Contrast-Driven Rubric Generation for Reliable and Interpretable Reward Modeling","created":"2026-03-09","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":"2512.23126","title":"InSPO: Unlocking Intrinsic Self-Reflection for LLM Preference Optimization","created":"2025-12-29","cited_by_count":11,"area":"alignment"},{"id":"2505.19770","title":"Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO","created":"2025-05-26","cited_by_count":10,"area":"alignment"},{"id":"2506.07326","title":"Reward Model Interpretability via Optimal and Pessimal Tokens","created":"2025-06-08","cited_by_count":10,"area":"alignment"},{"id":"2510.26707","title":"Value Drifts: Tracing Value Alignment During LLM Post-Training","created":"2025-10-30","cited_by_count":10,"area":"alignment"},{"id":"2502.16825","title":"Finding the Sweet Spot: Preference Data Construction for Scaling Preference Optimization","created":"2025-02-24","cited_by_count":9,"area":"alignment"},{"id":"2503.04647","title":"Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment","created":"2025-03-06","cited_by_count":9,"area":"alignment"},{"id":"2504.03612","title":"AIR: A Systematic Analysis of Annotations, Instructions, and Response Pairs in Preference Dataset","created":"2025-04-04","cited_by_count":9,"area":"alignment"},{"id":"2506.04463","title":"Aligning Large Language Models with Implicit Preferences from User-Generated Content","created":"2025-06-04","cited_by_count":9,"area":"alignment"},{"id":"2412.15282","title":"A Systematic Examination of Preference Learning through the Lens of Instruction-Following","created":"2024-12-18","cited_by_count":8,"area":"alignment"},{"id":"2502.03095","title":"Reveal the Mystery of DPO: The Connection between DPO and RL Algorithms","created":"2025-02-05","cited_by_count":8,"area":"alignment"},{"id":"2506.00569","title":"AutoMixAlign: Adaptive Data Mixing for Multi-Task Preference Optimization in LLMs","created":"2025-05-31","cited_by_count":8,"area":"alignment"},{"id":"2407.15229","title":"A Practical Analysis of Human Alignment with *PO","created":"2024-07-21","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":"2507.13158","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","created":"2025-07-17","cited_by_count":7,"area":"alignment"},{"id":"2502.00814","title":"Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling","created":"2025-02-02","cited_by_count":6,"area":"alignment"},{"id":"2505.02363","title":"SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning","created":"2025-05-05","cited_by_count":6,"area":"alignment"},{"id":"2505.10597","title":"Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment","created":"2025-05-15","cited_by_count":6,"area":"alignment"},{"id":"2506.14574","title":"TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization","created":"2025-06-17","cited_by_count":5,"area":"alignment"},{"id":"2502.11284","title":"Balancing the Budget: Understanding Trade-offs Between Supervised and Preference-Based Finetuning","created":"2025-02-16","cited_by_count":4,"area":"alignment"},{"id":"2503.13538","title":"From Demonstrations to Rewards: Alignment Without Explicit Human Preferences","created":"2025-03-15","cited_by_count":4,"area":"alignment"},{"id":"2410.06965","title":"Uncovering Factor Level Preferences to Improve Human-Model Alignment","created":"2024-10-09","cited_by_count":2,"area":"alignment"},{"id":"2501.03271","title":"DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization","created":"2025-01-05","cited_by_count":2,"area":"alignment"},{"id":"2506.04272","title":"Understanding the Impact of Sampling Quality in Direct Preference Optimization","created":"2025-06-03","cited_by_count":2,"area":"alignment"},{"id":"2510.03231","title":"Reward Models are Metrics in a Trench Coat","created":"2025-10-03","cited_by_count":2,"area":"alignment"},{"id":"2603.09692","title":"ActiveUltraFeedback: Efficient Preference Data Generation using Active Learning","created":"2026-03-10","cited_by_count":2,"area":"alignment"},{"id":"2608.31079","title":"Sycophantic Agreement Transfers with Neutral Data via Contrastive Preference Optimization","created":"2026-08-31","cited_by_count":2,"area":"alignment"},{"id":"2505.23557","title":"Learning Parametric Distributions from Samples and Preferences","created":"2025-05-29","cited_by_count":1,"area":"alignment"},{"id":"2506.00152","title":"Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective","created":"2025-05-30","cited_by_count":1,"area":"alignment"},{"id":"2506.00195","title":"Let Them Down Easy! Contextual Effects of LLM Guardrails on User Perceptions and Preferences","created":"2025-05-30","cited_by_count":1,"area":"alignment"},{"id":"2510.21090","title":"Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only","created":"2025-10-24","cited_by_count":1,"area":"alignment"},{"id":"2605.30619","title":"Reward Learning from Best-of-$N$ Preference Data: Targets, Tradeoffs, and Design Principles","created":"2026-05-28","cited_by_count":1,"area":"alignment"},{"id":"2506.03557","title":"BPO: Revisiting Preference Modeling in Direct Preference Optimization","created":"2025-06-04","cited_by_count":0,"area":"alignment"},{"id":"2507.01479","title":"Evaluating the Effectiveness of Direct Preference Optimization for Personalizing German Automatic Text Simplifications for Persons with Intellectual Disabilities","created":"2025-07-02","cited_by_count":0,"area":"alignment"},{"id":"2601.06108","title":"From RLHF to Direct Alignment: A Theoretical Unification of Preference Learning for Large Language Models","created":"2026-01-03","cited_by_count":0,"area":"alignment"},{"id":"2604.25895","title":"Three Models of RLHF Annotation: Extension, Evidence, and Authority","created":"2026-04-28","cited_by_count":0,"area":"alignment"},{"id":"2605.01831","title":"RMGAP: Benchmarking the Generalization of Reward Models across Diverse Preferences","created":"2026-05-03","cited_by_count":0,"area":"alignment"},{"id":"2608.09568","title":"Se-DPO: Self-Evolving Token Credit for Direct Preference Optimization","created":"2026-08-10","cited_by_count":0,"area":"alignment"},{"id":"2608.19748","title":"Truncate Bad, Upweight Good: BoN-Style Distillation via Rank-Based Classification","created":"2026-08-20","cited_by_count":0,"area":"alignment"},{"id":"2609.06893","title":"Towards Bridging the Gap Between Offline and Iterative Alignment via Preference Distillation","created":"2026-09-07","cited_by_count":0,"area":"alignment"},{"id":"2609.12607","title":"Direct Preference Density Alignment for Conversational Audio Equalization","created":"2026-09-11","cited_by_count":0,"area":"alignment"}],"next_cursor":null}