{"total":22,"rows":[{"id":"2309.10105","title":"Understanding Catastrophic Forgetting in Language Models via Implicit Inference","created":"2023-09-18","cited_by_count":144,"area":"alignment"},{"id":"2402.01109","title":"Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack","created":"2024-02-02","cited_by_count":115,"area":"alignment"},{"id":"2402.06886","title":"Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF","created":"2024-02-10","cited_by_count":41,"area":"alignment"},{"id":"2102.12466","title":"Information Directed Reward Learning for Reinforcement Learning","created":"2021-02-24","cited_by_count":24,"area":"alignment"},{"id":"2412.08812","title":"Test-Time Alignment via Hypothesis Reweighting","created":"2024-12-11","cited_by_count":11,"area":"alignment"},{"id":"2410.21349","title":"FALCON: Feedback-driven Adaptive Long/short-term memory reinforced Coding Optimization system","created":"2024-10-28","cited_by_count":8,"area":"alignment"},{"id":"2402.14760","title":"Generalizing Reward Modeling for Out-of-Distribution Preference Learning","created":"2024-02-22","cited_by_count":6,"area":"alignment"},{"id":"2510.10085","title":"Pharmacist: Safety Alignment Data Curation for Large Language Models against Harmful Fine-tuning","created":"2025-10-11","cited_by_count":6,"area":"alignment"},{"id":"2405.00438","title":"MetaRM: Shifted Distributions Alignment via Meta-Learning","created":"2024-05-01","cited_by_count":4,"area":"alignment"},{"id":"2508.09473","title":"NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs","created":"2025-08-13","cited_by_count":4,"area":"alignment"},{"id":"2411.06568","title":"Meta-Learning Objectives for Preference Optimization","created":"2024-11-10","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":"2508.09016","title":"A Survey on Training-free Alignment of Large Language Models","created":"2025-08-12","cited_by_count":2,"area":"alignment"},{"id":"2606.21089","title":"Repeated post-training is not Self-improving: Diagnosing Scientific Amnesia in Continual DPO Pipelines","created":"2026-06-17","cited_by_count":1,"area":"alignment"},{"id":"2205.07882","title":"Aligning Robot Representations with Humans","created":"2022-05-15","cited_by_count":0,"area":"alignment"},{"id":"2510.15728","title":"RLAF: Reinforcement Learning from Automaton Feedback","created":"2025-10-17","cited_by_count":0,"area":"alignment"},{"id":"2512.20974","title":"Meta-RL with Bayesian Linear Task Models","created":"2025-12-24","cited_by_count":0,"area":"alignment"},{"id":"2606.07629","title":"Large Language Models Should Learn Personalized Rather Than Aggregated Human Preferences","created":"2026-05-30","cited_by_count":0,"area":"alignment"},{"id":"2606.07970","title":"Defending Against Malicious Finetuning by Scaling Train-time Adversarial Attacks","created":"2026-06-06","cited_by_count":0,"area":"alignment"},{"id":"2606.09866","title":"Two to Tango: Coupled Task-Reference Selection for Safe LLM Fine-tuning","created":"2026-06-01","cited_by_count":0,"area":"alignment"},{"id":"2607.13315","title":"Meta-Learning Preferences for Multilingual LLM Alignment","created":"2026-07-14","cited_by_count":0,"area":"alignment"},{"id":"2608.06105","title":"Does Latent Context Help? A Controlled Evaluation of Inverse Reinforcement Learning in Arctic Shipping","created":"2026-08-06","cited_by_count":0,"area":"alignment"}],"next_cursor":null}