{"total":38,"rows":[{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154,"area":"alignment"},{"id":"2309.10105","title":"Understanding Catastrophic Forgetting in Language Models via Implicit Inference","created":"2023-09-18","cited_by_count":144,"area":"alignment"},{"id":"2310.06762","title":"TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models","created":"2023-10-10","cited_by_count":66,"area":"alignment"},{"id":"2310.04799","title":"Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New Languages","created":"2023-10-07","cited_by_count":54,"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":"2510.04309","title":"Activation Steering with a Feedback Controller","created":"2025-10-05","cited_by_count":15,"area":"alignment"},{"id":"2406.04854","title":"Uncertainty Aware Learning for Language Model Alignment","created":"2024-06-07","cited_by_count":13,"area":"alignment"},{"id":"2410.02205","title":"Aligning with Logic: Measuring, Evaluating and Improving Logical Preference Consistency in Large Language Models","created":"2024-10-03","cited_by_count":12,"area":"alignment"},{"id":"2506.20495","title":"ReCode: Updating Code API Knowledge with Reinforcement Learning","created":"2025-06-25","cited_by_count":12,"area":"alignment"},{"id":"2403.03419","title":"Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization","created":"2024-03-06","cited_by_count":11,"area":"alignment"},{"id":"2410.05102","title":"SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks","created":"2024-10-07","cited_by_count":9,"area":"alignment"},{"id":"2407.02987","title":"LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models","created":"2024-07-03","cited_by_count":7,"area":"alignment"},{"id":"2407.03856","title":"Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation","created":"2024-07-04","cited_by_count":7,"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":"2407.00693","title":"BAPO: Base-Anchored Preference Optimization for Overcoming Forgetting in Large Language Models Personalization","created":"2024-06-30","cited_by_count":6,"area":"alignment"},{"id":"2605.01123","title":"PERSA: Reinforcement Learning for Professor-Style Personalized Feedback with LLMs","created":"2026-05-01","cited_by_count":6,"area":"alignment"},{"id":"2404.18410","title":"Mixture-of-Instructions: Aligning Large Language Models via Mixture Prompting","created":"2024-04-29","cited_by_count":4,"area":"alignment"},{"id":"2509.23765","title":"Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality","created":"2025-09-28","cited_by_count":4,"area":"alignment"},{"id":"2604.17215","title":"Continual Safety Alignment via Gradient-Based Sample Selection","created":"2026-04-19","cited_by_count":4,"area":"alignment"},{"id":"2404.10306","title":"Balancing Speciality and Versatility: A Coarse to Fine Framework for Mitigating Catastrophic Forgetting in Large Language Models","created":"2024-04-16","cited_by_count":3,"area":"alignment"},{"id":"2502.08657","title":"Refining Positive and Toxic Samples for Dual Safety Self-Alignment of LLMs with Minimal Human Interventions","created":"2025-02-08","cited_by_count":3,"area":"alignment"},{"id":"2508.13993","title":"Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization","created":"2025-08-19","cited_by_count":3,"area":"alignment"},{"id":"2601.09253","title":"RIFT: Repurposing Negative Samples via Reward-Informed Fine-Tuning","created":"2026-01-14","cited_by_count":3,"area":"alignment"},{"id":"2602.08813","title":"Robust Policy Optimization to Prevent Catastrophic Forgetting","created":"2026-02-09","cited_by_count":3,"area":"alignment"},{"id":"2607.25614","title":"MemSFT: Mitigating Alignment Tax with an External Parametric Memory","created":"2026-07-28","cited_by_count":3,"area":"alignment"},{"id":"2502.19463","title":"Hedging and Non-Affirmation: Quantifying LLM Alignment on Questions of Human Rights","created":"2025-02-26","cited_by_count":1,"area":"alignment"},{"id":"2602.03073","title":"TMS: Trajectory-Mixed Supervision for Reward-Free, On-Policy SFT","created":"2026-02-03","cited_by_count":1,"area":"alignment"},{"id":"2605.29275","title":"Prompt-Level Reward Specifications for Open-Ended Post-Training","created":"2026-05-28","cited_by_count":1,"area":"alignment"},{"id":"2609.14896","title":"Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning","created":"2026-09-14","cited_by_count":1,"area":"alignment"},{"id":"2406.18954","title":"Alignment For Performance Improvement in Conversation Bots","created":"2024-06-27","cited_by_count":0,"area":"alignment"},{"id":"2503.18089","title":"$D^2LoRA$: Data-Driven LoRA Initialization for Low Resource Tasks","created":"2025-03-23","cited_by_count":0,"area":"alignment"},{"id":"2604.17691","title":"SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models","created":"2026-04-20","cited_by_count":0,"area":"alignment"},{"id":"2605.26293","title":"CroCo: Cross-Lingual Contrastive Preference Tuning on Self-Generations","created":"2026-05-25","cited_by_count":0,"area":"alignment"},{"id":"2606.28998","title":"Reward-Free Code Alignment from Pretrained or Fine-Tuned LLM: Unpacking the Trade-offs for Code Generation","created":"2026-06-27","cited_by_count":0,"area":"alignment"},{"id":"2608.06792","title":"Progressive Alignment of Recommender Foundation Model through Multi-Phase Post-Training","created":"2026-08-07","cited_by_count":0,"area":"alignment"},{"id":"2608.24192","title":"Preference Data Selection for Mitigating the Alignment Tax in Large Language Models","created":"2026-08-25","cited_by_count":0,"area":"alignment"},{"id":"2609.16532","title":"Style-Debiased DPO: Updating LLM Knowledge with Factuality-Aware Synthetic Preference Data","created":"2026-09-15","cited_by_count":0,"area":"alignment"},{"id":"2609.36748","title":"Generalizable Lifelong Model Editing via Preference Optimization","created":"2026-09-29","cited_by_count":0,"area":"alignment"}],"next_cursor":null}