{"total":21,"rows":[{"id":"2409.20370","title":"The Perfect Blend: Redefining RLHF with Mixture of Judges","created":"2024-09-30","cited_by_count":43,"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":"2509.11452","title":"Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting","created":"2025-09-14","cited_by_count":23,"area":"alignment"},{"id":"2501.19358","title":"The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking","created":"2025-01-31","cited_by_count":18,"area":"alignment"},{"id":"2409.02795","title":"Towards a Unified View of Preference Learning for Large Language Models: A Survey","created":"2024-09-04","cited_by_count":17,"area":"alignment"},{"id":"2507.05197","title":"Pre-Trained Policy Discriminators are General Reward Models","created":"2025-07-07","cited_by_count":15,"area":"alignment"},{"id":"2410.14940","title":"Baichuan Alignment Technical Report","created":"2024-10-19","cited_by_count":6,"area":"alignment"},{"id":"2504.15843","title":"Pre-DPO: Improving Data Utilization in Direct Preference Optimization Using a Guiding Reference Model","created":"2025-04-22","cited_by_count":6,"area":"alignment"},{"id":"2510.08697","title":"BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution","created":"2025-10-09","cited_by_count":6,"area":"alignment"},{"id":"2503.04249","title":"How to Mitigate Overfitting in Weak-to-strong Generalization?","created":"2025-03-06","cited_by_count":3,"area":"alignment"},{"id":"2603.17044","title":"Do Understanding and Generation Fight? A Diagnostic Study of DPO for Unified Multimodal Models","created":"2026-03-17","cited_by_count":3,"area":"alignment"},{"id":"2503.22115","title":"Beyond Single-Sentence Prompts: Upgrading Value Alignment Benchmarks with Dialogues and Stories","created":"2025-03-28","cited_by_count":2,"area":"alignment"},{"id":"2505.08849","title":"Improved Algorithms for Differentially Private Language Model Alignment","created":"2025-05-13","cited_by_count":2,"area":"alignment"},{"id":"2602.06869","title":"Uncovering Cross-Objective Interference in Multi-Objective Alignment","created":"2026-02-06","cited_by_count":2,"area":"alignment"},{"id":"2505.19700","title":"Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models","created":"2025-05-26","cited_by_count":1,"area":"alignment"},{"id":"2605.20285","title":"Introspective X Training: Feedback Conditioning Improves Scaling Across all LLM Training Stages","created":"2026-05-19","cited_by_count":1,"area":"alignment"},{"id":"2410.01789","title":"Investigating on RLHF methodology","created":"2024-10-02","cited_by_count":0,"area":"alignment"},{"id":"2602.03265","title":"Beyond Suffixes: Token Position in GCG Adversarial Attacks on Large Language Models","created":"2026-02-03","cited_by_count":0,"area":"alignment"},{"id":"2604.25702","title":"Backtranslation Augmented Direct Preference Optimization for Neural Machine Translation","created":"2026-04-28","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"},{"id":"2610.15207","title":"Exploring Jailbreak Vulnerability Across Depth-Based Dynamic Inference in Large Language Models","created":"2026-10-10","cited_by_count":0,"area":"alignment"}],"next_cursor":null}