{"total":15,"rows":[{"id":"2504.12501","title":"Reinforcement Learning from Human Feedback","created":"2025-04-16","cited_by_count":58,"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":"2505.13388","title":"R3: Robust Rubric-Agnostic Reward Models","created":"2025-05-19","cited_by_count":23,"area":"alignment"},{"id":"2509.11864","title":"NeuroStrike: Neuron-Level Attacks on Aligned LLMs","created":"2025-09-15","cited_by_count":22,"area":"alignment"},{"id":"2607.15161","title":"On-Policy Delta Distillation","created":"2026-07-16","cited_by_count":15,"area":"alignment"},{"id":"2506.04118","title":"Guided Speculative Inference for Efficient Test-Time Alignment of LLMs","created":"2025-06-04","cited_by_count":11,"area":"alignment"},{"id":"2503.19041","title":"LookAhead Tuning: Safer Language Models via Partial Answer Previews","created":"2025-03-24","cited_by_count":7,"area":"alignment"},{"id":"2509.25762","title":"OPPO: Accelerating PPO-based RLHF via Pipeline Overlap","created":"2025-09-30","cited_by_count":3,"area":"alignment"},{"id":"2507.20067","title":"PITA: Preference-Guided Inference-Time Alignment for LLM Post-Training","created":"2025-07-26","cited_by_count":2,"area":"alignment"},{"id":"2509.13079","title":"When Inverse Data Outperforms: Exploring the Pitfalls of Mixed Data in Multi-Stage Fine-Tuning","created":"2025-09-16","cited_by_count":2,"area":"alignment"},{"id":"2604.08723","title":"Decomposing the Delta: What Do Models Actually Learn from Preference Pairs?","created":"2026-04-09","cited_by_count":1,"area":"alignment"},{"id":"2510.05534","title":"Revisiting Self-Play Preference Optimization: On the Role of Prompt Difficulty","created":"2025-10-07","cited_by_count":0,"area":"alignment"},{"id":"2605.10863","title":"DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise Optimization","created":"2026-05-11","cited_by_count":0,"area":"alignment"},{"id":"2606.30339","title":"REAR: Test-time Preference Realignment through Reward Decomposition","created":"2026-06-29","cited_by_count":0,"area":"alignment"},{"id":"2608.30842","title":"Thesis Proposal: Toward a Human-Centered and Perspective-Aware Framework for Reproducible ML Evaluation and AI Alignment","created":"2026-08-31","cited_by_count":0,"area":"alignment"}],"next_cursor":null}