{"total":53,"rows":[{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499,"area":"alignment"},{"id":"2402.13228","title":"Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive","created":"2024-02-20","cited_by_count":241,"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":"2506.01937","title":"RewardBench 2: Advancing Reward Model Evaluation","created":"2025-06-02","cited_by_count":150,"area":"alignment"},{"id":"2402.08925","title":"MaxMin-RLHF: Alignment with Diverse Human Preferences","created":"2024-02-14","cited_by_count":123,"area":"alignment"},{"id":"2410.09724","title":"Taming Overconfidence in LLMs: Reward Calibration in RLHF","created":"2024-10-13","cited_by_count":112,"area":"alignment"},{"id":"2403.08635","title":"Human Alignment of Large Language Models through Online Preference Optimisation","created":"2024-03-13","cited_by_count":91,"area":"alignment"},{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90,"area":"alignment"},{"id":"2402.04833","title":"Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning","created":"2024-02-07","cited_by_count":85,"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":"2402.15018","title":"Unintended Impacts of LLM Alignment on Global Representation","created":"2024-02-22","cited_by_count":66,"area":"alignment"},{"id":"2405.19332","title":"Self-Exploring Language Models: Active Preference Elicitation for Online Alignment","created":"2024-05-29","cited_by_count":63,"area":"alignment"},{"id":"2411.04427","title":"One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity","created":"2024-11-07","cited_by_count":58,"area":"alignment"},{"id":"2504.12501","title":"Reinforcement Learning from Human Feedback","created":"2025-04-16","cited_by_count":58,"area":"alignment"},{"id":"2410.08193","title":"GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment","created":"2024-10-10","cited_by_count":54,"area":"alignment"},{"id":"2406.14144","title":"Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons","created":"2024-06-20","cited_by_count":53,"area":"alignment"},{"id":"2407.07880","title":"Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization","created":"2024-07-10","cited_by_count":53,"area":"alignment"},{"id":"2403.17031","title":"The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization","created":"2024-03-24","cited_by_count":50,"area":"alignment"},{"id":"2405.19107","title":"Offline Regularised Reinforcement Learning for Large Language Models Alignment","created":"2024-05-29","cited_by_count":48,"area":"alignment"},{"id":"2405.20495","title":"Transfer Q Star: Principled Decoding for LLM Alignment","created":"2024-05-30","cited_by_count":48,"area":"alignment"},{"id":"2403.19270","title":"sDPO: Don't Use Your Data All at Once","created":"2024-03-28","cited_by_count":46,"area":"alignment"},{"id":"2402.12366","title":"A Critical Evaluation of AI Feedback for Aligning Large Language Models","created":"2024-02-19","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":"2405.19262","title":"Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models","created":"2024-05-29","cited_by_count":32,"area":"alignment"},{"id":"2405.20653","title":"Mind the Inconspicuous: Revealing the Hidden Weakness in Aligned LLMs' Refusal Boundaries","created":"2024-05-31","cited_by_count":28,"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":"2407.08770","title":"Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing","created":"2024-07-11","cited_by_count":23,"area":"alignment"},{"id":"2508.10858","title":"Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation","created":"2025-08-14","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":"2405.13432","title":"Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction","created":"2024-05-22","cited_by_count":18,"area":"alignment"},{"id":"2405.14953","title":"MallowsPO: Fine-Tune Your LLM with Preference Dispersions","created":"2024-05-23","cited_by_count":18,"area":"alignment"},{"id":"2402.11296","title":"Dissecting Human and LLM Preferences","created":"2024-02-17","cited_by_count":17,"area":"alignment"},{"id":"2402.07896","title":"Suppressing Pink Elephants with Direct Principle Feedback","created":"2024-02-12","cited_by_count":15,"area":"alignment"},{"id":"2410.08067","title":"Reward-Augmented Data Enhances Direct Preference Alignment of LLMs","created":"2024-10-10","cited_by_count":10,"area":"alignment"},{"id":"2405.01511","title":"D2PO: Discriminator-Guided DPO with Response Evaluation Models","created":"2024-05-02","cited_by_count":9,"area":"alignment"},{"id":"2406.01514","title":"Decoupled Alignment for Robust Plug-and-Play Adaptation","created":"2024-06-03","cited_by_count":9,"area":"alignment"},{"id":"2408.05094","title":"Unlocking Decoding-time Controllability: Gradient-Free Multi-Objective Alignment with Contrastive Prompts","created":"2024-08-09","cited_by_count":9,"area":"alignment"},{"id":"2410.11055","title":"Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only","created":"2024-10-14","cited_by_count":9,"area":"alignment"},{"id":"2506.04721","title":"SPARTA ALIGNMENT: Collectively Aligning Multiple Language Models through Combat","created":"2025-06-05","cited_by_count":9,"area":"alignment"},{"id":"2402.02479","title":"BRAIn: Bayesian Reward-conditioned Amortized Inference for natural language generation from feedback","created":"2024-02-04","cited_by_count":7,"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":"2412.17696","title":"Understanding the Logic of Direct Preference Alignment through Logic","created":"2024-12-23","cited_by_count":5,"area":"alignment"},{"id":"2504.06020","title":"Information-Theoretic Reward Decomposition for Generalizable RLHF","created":"2025-04-08","cited_by_count":5,"area":"alignment"},{"id":"2504.07856","title":"Dual-Difficulty Curriculum Learning for Direct Preference Optimization","created":"2025-04-10","cited_by_count":5,"area":"alignment"},{"id":"2505.23316","title":"Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPO","created":"2025-05-29","cited_by_count":5,"area":"alignment"},{"id":"2501.18511","title":"WILDCHAT-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training","created":"2025-01-30","cited_by_count":4,"area":"alignment"},{"id":"2509.23542","title":"On the Shelf Life of Fine-Tuned LLM-Judges: Future-Proofing, Backward-Compatibility, and Question Generalization","created":"2025-09-28","cited_by_count":3,"area":"alignment"},{"id":"2406.16377","title":"On the Transformations across Reward Model, Parameter Update, and In-Context Prompt","created":"2024-06-24","cited_by_count":1,"area":"alignment"},{"id":"2510.06670","title":"PIKA: Expert-Level Synthetic Datasets for Post-Training Alignment from Scratch","created":"2025-10-08","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":"2605.20834","title":"Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable Alignment","created":"2026-05-20","cited_by_count":1,"area":"alignment"},{"id":"2507.03673","title":"TACOS: Open Tagging and Comparative Scoring for Instruction Fine-Tuning Data Selection","created":"2025-07-04","cited_by_count":0,"area":"alignment"},{"id":"2509.22633","title":"Towards Efficient Online Exploration for Reinforcement Learning with Human Feedback","created":"2025-09-26","cited_by_count":0,"area":"alignment"}],"next_cursor":null}