{"total":34,"rows":[{"id":"2405.16436","title":"Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer","created":"2024-05-26","cited_by_count":109,"area":"alignment"},{"id":"2407.10490","title":"Learning Dynamics of LLM Finetuning","created":"2024-07-15","cited_by_count":95,"area":"alignment"},{"id":"2408.06266","title":"Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment","created":"2024-08-12","cited_by_count":46,"area":"alignment"},{"id":"2503.03710","title":"Improving LLM Safety Alignment with Dual-Objective Optimization","created":"2025-03-05","cited_by_count":43,"area":"alignment"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2409.13474","title":"Alternate Preference Optimization for Unlearning Factual Knowledge in Large Language Models","created":"2024-09-20","cited_by_count":33,"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":"2409.11564","title":"Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey","created":"2024-09-17","cited_by_count":23,"area":"alignment"},{"id":"2410.03523","title":"A Probabilistic Perspective on Unlearning and Alignment for Large Language Models","created":"2024-10-04","cited_by_count":21,"area":"alignment"},{"id":"2405.13820","title":"Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching","created":"2024-05-22","cited_by_count":17,"area":"alignment"},{"id":"2507.21183","title":"MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge","created":"2025-07-27","cited_by_count":15,"area":"alignment"},{"id":"2508.07172","title":"Gradient Surgery for Safe LLM Fine-Tuning","created":"2025-08-10","cited_by_count":11,"area":"alignment"},{"id":"2411.13611","title":"DSTC: Direct Preference Learning with Only Self-Generated Tests and Code to Improve Code LMs","created":"2024-11-20","cited_by_count":9,"area":"alignment"},{"id":"2405.11870","title":"Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process","created":"2024-05-20","cited_by_count":8,"area":"alignment"},{"id":"2405.12961","title":"Aligning Transformers with Continuous Feedback via Energy Rank Alignment","created":"2024-05-21","cited_by_count":7,"area":"alignment"},{"id":"2406.12606","title":"Not Everything is All You Need: Toward Low-Redundant Optimization for Large Language Model Alignment","created":"2024-06-18","cited_by_count":7,"area":"alignment"},{"id":"2504.14452","title":"ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data","created":"2025-04-20","cited_by_count":6,"area":"alignment"},{"id":"2503.22948","title":"SUV: Scalable Large Language Model Copyright Compliance with Regularized Selective Unlearning","created":"2025-03-29","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":"2510.04773","title":"Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearning","created":"2025-10-06","cited_by_count":3,"area":"alignment"},{"id":"2503.13690","title":"Atyaephyra at SemEval-2025 Task 4: Low-Rank Negative Preference Optimization","created":"2025-03-17","cited_by_count":2,"area":"alignment"},{"id":"2504.06659","title":"Leveraging Machine Unlearning for Cost-Efficient Preference Alignment","created":"2025-04-09","cited_by_count":2,"area":"alignment"},{"id":"2507.17107","title":"Reinforcement Learning Fine-Tunes a Sparse Subnetwork in Large Language Models","created":"2025-07-23","cited_by_count":2,"area":"alignment"},{"id":"2512.00778","title":"What Is Preference Optimization Doing, and Why?","created":"2025-11-30","cited_by_count":2,"area":"alignment"},{"id":"2502.01472","title":"FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model","created":"2025-02-03","cited_by_count":1,"area":"alignment"},{"id":"2607.29246","title":"Don't Mix Rewards, Mix Policies: Policy Decomposition and Optimization for Multi-Reward RL","created":"2026-07-31","cited_by_count":1,"area":"alignment"},{"id":"2507.20566","title":"Unlearning of Knowledge Graph Embedding via Preference Optimization","created":"2025-07-28","cited_by_count":0,"area":"alignment"},{"id":"2511.02623","title":"The Realignment Problem: When Right becomes Wrong in LLMs","created":"2025-11-04","cited_by_count":0,"area":"alignment"},{"id":"2603.16417","title":"Via Negativa for AI Alignment: Why Negative Constraints Are Structurally Superior to Positive Preferences","created":"2026-03-17","cited_by_count":0,"area":"alignment"},{"id":"2604.18966","title":"Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Training","created":"2026-04-21","cited_by_count":0,"area":"alignment"},{"id":"2606.12505","title":"Boosting Direct Preference Optimization with Penalization","created":"2026-06-10","cited_by_count":0,"area":"alignment"},{"id":"2607.19371","title":"Mitigating Scaffolding Collapse in Socratic Tutors via Representation Alignment","created":"2026-06-15","cited_by_count":0,"area":"alignment"},{"id":"2609.08244","title":"CUNO: Curriculum and Preference Optimization for Stable Graph Unlearning under Mass Deletion","created":"2026-09-08","cited_by_count":0,"area":"alignment"},{"id":"2610.01323","title":"TRACE: Trajectory Return Attribution and Contrastive Erasure for Multi-Turn Safety","created":"2026-10-01","cited_by_count":0,"area":"alignment"}],"next_cursor":null}