{"total":21,"rows":[{"id":"2410.03642","title":"Aligning LLMs with Individual Preferences via Interaction","created":"2024-10-04","cited_by_count":63,"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":"2410.09412","title":"FB-Bench: A Fine-Grained Multi-Task Benchmark for Evaluating LLMs' Responsiveness to Human Feedback","created":"2024-10-12","cited_by_count":11,"area":"alignment"},{"id":"2410.19720","title":"2D-DPO: Scaling Direct Preference Optimization with 2-Dimensional Supervision","created":"2024-10-25","cited_by_count":6,"area":"alignment"},{"id":"2410.21159","title":"CURATe: Benchmarking Personalised Alignment of Conversational AI Assistants","created":"2024-10-28","cited_by_count":5,"area":"alignment"},{"id":"2506.02553","title":"Response-Level Rewards Are All You Need for Online Reinforcement Learning in LLMs: A Mathematical Perspective","created":"2025-06-03","cited_by_count":5,"area":"alignment"},{"id":"2510.02341","title":"DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning","created":"2025-09-27","cited_by_count":5,"area":"alignment"},{"id":"2508.19922","title":"HEAL: A Hypothesis-Based Preference-Aware Analysis Framework","created":"2025-08-27","cited_by_count":4,"area":"alignment"},{"id":"2604.02507","title":"Reinforcement Learning from Human Feedback: A Statistical Perspective","created":"2026-04-02","cited_by_count":4,"area":"alignment"},{"id":"2502.12678","title":"Multi-Step Alignment as Markov Games: An Optimistic Online Gradient Descent Approach with Convergence Guarantees","created":"2025-02-18","cited_by_count":3,"area":"alignment"},{"id":"2604.18943","title":"Personalized Benchmarking: Evaluating LLMs by Individual Preferences","created":"2026-04-21","cited_by_count":3,"area":"alignment"},{"id":"2511.10656","title":"Preference Orchestrator: Prompt-Aware Multi-Objective Alignment for Large Language Models","created":"2025-11-03","cited_by_count":2,"area":"alignment"},{"id":"2606.09850","title":"Mechanistic Analysis of Alignment Algorithms in Language Models","created":"2026-05-09","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":"2508.14947","title":"Linear Preference Optimization: Decoupled Gradient Control via Absolute Regularization","created":"2025-08-20","cited_by_count":1,"area":"alignment"},{"id":"2507.07725","title":"Not All Preferences are What You Need for Post-Training: Selective Alignment Strategy for Preference Optimization","created":"2025-07-10","cited_by_count":0,"area":"alignment"},{"id":"2603.04974","title":"VRM: Teaching Reward Models to Understand Authentic Human Preferences","created":"2026-03-05","cited_by_count":0,"area":"alignment"},{"id":"2605.04477","title":"Data-dependent Exploration for Online Reinforcement Learning from Human Feedback","created":"2026-05-06","cited_by_count":0,"area":"alignment"},{"id":"2606.30116","title":"Open Problems in Constitutional Preference Reconstruction","created":"2026-06-29","cited_by_count":0,"area":"alignment"},{"id":"2607.00572","title":"HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment","created":"2026-07-01","cited_by_count":0,"area":"alignment"},{"id":"2609.08634","title":"Suan: Rectifying Direct Preference Safety Alignment in Large Language Models","created":"2026-09-08","cited_by_count":0,"area":"alignment"}],"next_cursor":null}