{"total":37,"rows":[{"id":"2506.01937","title":"RewardBench 2: Advancing Reward Model Evaluation","created":"2025-06-02","cited_by_count":150,"area":"alignment"},{"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":"2503.06358","title":"Language Model Personalization via Reward Factorization","created":"2025-03-08","cited_by_count":31,"area":"alignment"},{"id":"2502.01208","title":"On Almost Surely Safe Alignment of Large Language Models at Inference-Time","created":"2025-02-03","cited_by_count":14,"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":"2506.07326","title":"Reward Model Interpretability via Optimal and Pessimal Tokens","created":"2025-06-08","cited_by_count":10,"area":"alignment"},{"id":"2503.17338","title":"Capturing Individual Human Preferences with Reward Features","created":"2025-03-21","cited_by_count":8,"area":"alignment"},{"id":"2501.15453","title":"Data-adaptive Safety Rules for Training Reward Models","created":"2025-01-26","cited_by_count":6,"area":"alignment"},{"id":"2502.12530","title":"Translate Policy to Language: Flow Matching Generated Rewards for LLM Explanations","created":"2025-02-18","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":"2501.13264","title":"OpenGenAlign: A Preference Dataset and Benchmark for Trustworthy Reward Modeling in Open-Ended, Long-Context Generation","created":"2025-01-22","cited_by_count":5,"area":"alignment"},{"id":"2602.03876","title":"GOPO: Policy Optimization using Ranked Rewards","created":"2026-02-01","cited_by_count":5,"area":"alignment"},{"id":"2504.13134","title":"Energy-Based Reward Models for Robust Language Model Alignment","created":"2025-04-17","cited_by_count":4,"area":"alignment"},{"id":"2512.10575","title":"RoleRMBench & RoleRM: Towards Reward Modeling for Profile-Based Role Play in Dialogue Systems","created":"2025-12-11","cited_by_count":4,"area":"alignment"},{"id":"2503.10927","title":"OASST-ETC Dataset: Alignment Signals from Eye-tracking Analysis of LLM Responses","created":"2025-03-13","cited_by_count":3,"area":"alignment"},{"id":"2601.20838","title":"Reward Models Inherit Value Biases from Pretraining","created":"2026-01-28","cited_by_count":3,"area":"alignment"},{"id":"2602.20670","title":"CAMEL: Confidence-Gated Reflection for Reward Modeling","created":"2026-02-24","cited_by_count":3,"area":"alignment"},{"id":"2410.18127","title":"Holistic Utility Preference Learning for Listwise Alignment","created":"2024-10-17","cited_by_count":2,"area":"alignment"},{"id":"2502.17173","title":"Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from Scratch","created":"2025-02-24","cited_by_count":2,"area":"alignment"},{"id":"2505.20088","title":"Multi-Domain Explainability of Preferences","created":"2025-05-26","cited_by_count":2,"area":"alignment"},{"id":"2509.21798","title":"Evaluating and Improving Cultural Awareness of Reward Models for LLM Alignment","created":"2025-09-26","cited_by_count":2,"area":"alignment"},{"id":"2509.23564","title":"Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment","created":"2025-09-28","cited_by_count":2,"area":"alignment"},{"id":"2603.12795","title":"SteerRM: Debiasing Reward Models via Sparse Autoencoders","created":"2026-03-13","cited_by_count":2,"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":"2511.20668","title":"PIRA: Preference-Oriented Instruction-Tuned Reward Models with Dual Aggregation","created":"2025-11-14","cited_by_count":1,"area":"alignment"},{"id":"2512.06343","title":"When Distance Distracts: Representation Distance Bias in BT-Loss for Reward Models","created":"2025-12-06","cited_by_count":1,"area":"alignment"},{"id":"2602.12660","title":"Learning Ordinal Probabilistic Reward from Preferences","created":"2026-02-13","cited_by_count":1,"area":"alignment"},{"id":"2605.04831","title":"StoryAlign: Evaluating and Training Reward Models for Story Generation","created":"2026-05-06","cited_by_count":1,"area":"alignment"},{"id":"2606.09073","title":"A Unifying Lens on Reward Uncertainty in RLHF","created":"2026-06-08","cited_by_count":1,"area":"alignment"},{"id":"2505.10775","title":"A Systematic Analysis of Base Model Choice for Reward Modeling","created":"2025-05-16","cited_by_count":0,"area":"alignment"},{"id":"2510.09330","title":"Safety Game: Inference-Time Alignment of Black-Box LLMs via Constrained Optimization","created":"2025-10-10","cited_by_count":0,"area":"alignment"},{"id":"2512.24693","title":"MUSIC: MUlti-Step Instruction Contrast for Multi-Turn Reward Models","created":"2025-12-31","cited_by_count":0,"area":"alignment"},{"id":"2601.16987","title":"Evaluating Reward Model Generalization via Pairwise Maximum Discrepancy Competitions","created":"2026-01-05","cited_by_count":0,"area":"alignment"},{"id":"2605.27355","title":"Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases","created":"2026-05-26","cited_by_count":0,"area":"alignment"},{"id":"2609.33086","title":"From Constitutions to Control: Interpretable Rewards for Aligning Language Models","created":"2026-09-27","cited_by_count":0,"area":"alignment"},{"id":"2609.33803","title":"Diffusion Reward Models","created":"2026-09-27","cited_by_count":0,"area":"alignment"},{"id":"2609.34345","title":"CRISP: Cultural Reward Modeling for Implicit Situated Propriety","created":"2026-09-28","cited_by_count":0,"area":"alignment"}],"next_cursor":null}