{"total":49,"rows":[{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723,"area":"alignment"},{"id":"2401.10020","title":"Self-Rewarding Language Models","created":"2024-01-18","cited_by_count":681,"area":"alignment"},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467,"area":"alignment"},{"id":"2310.01377","title":"UltraFeedback: Boosting Language Models with Scaled AI Feedback","created":"2023-10-02","cited_by_count":406,"area":"alignment"},{"id":"2310.02949","title":"Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models","created":"2023-10-04","cited_by_count":297,"area":"alignment"},{"id":"2307.10928","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","created":"2023-07-20","cited_by_count":201,"area":"alignment"},{"id":"2309.06256","title":"Mitigating the Alignment Tax of RLHF","created":"2023-09-12","cited_by_count":183,"area":"alignment"},{"id":"2302.02676","title":"Chain of Hindsight Aligns Language Models with Feedback","created":"2023-02-06","cited_by_count":148,"area":"alignment"},{"id":"2402.16192","title":"Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing","created":"2024-02-25","cited_by_count":74,"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":"2404.09656","title":"Learn Your Reference Model for Real Good Alignment","created":"2024-04-15","cited_by_count":57,"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":"2404.14723","title":"Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks","created":"2024-04-23","cited_by_count":35,"area":"alignment"},{"id":"2402.13605","title":"KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge","created":"2024-02-21","cited_by_count":33,"area":"alignment"},{"id":"2409.15360","title":"Reward-Robust RLHF in LLMs","created":"2024-09-18","cited_by_count":32,"area":"alignment"},{"id":"2406.10957","title":"Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence","created":"2024-06-16","cited_by_count":31,"area":"alignment"},{"id":"2405.05008","title":"ADELIE: Aligning Large Language Models on Information Extraction","created":"2024-05-08","cited_by_count":24,"area":"alignment"},{"id":"2406.10288","title":"Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language Models","created":"2024-06-12","cited_by_count":17,"area":"alignment"},{"id":"2408.04614","title":"Better Alignment with Instruction Back-and-Forth Translation","created":"2024-08-08","cited_by_count":16,"area":"alignment"},{"id":"2410.10862","title":"Superficial Safety Alignment Hypothesis","created":"2024-10-07","cited_by_count":14,"area":"alignment"},{"id":"2506.14681","title":"Massive Supervised Fine-tuning Experiments Reveal How Data, Layer, and Training Factors Shape LLM Alignment Quality","created":"2025-06-17","cited_by_count":14,"area":"alignment"},{"id":"2510.26707","title":"Value Drifts: Tracing Value Alignment During LLM Post-Training","created":"2025-10-30","cited_by_count":10,"area":"alignment"},{"id":"2407.03051","title":"Improving Conversational Abilities of Quantized Large Language Models via Direct Preference Alignment","created":"2024-07-03","cited_by_count":9,"area":"alignment"},{"id":"2505.17072","title":"Safety Alignment Can Be Not Superficial With Explicit Safety Signals","created":"2025-05-19","cited_by_count":9,"area":"alignment"},{"id":"2505.18720","title":"Optimal Transport-Based Token Weighting scheme for Enhanced Preference Optimization","created":"2025-05-24","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":"2505.02363","title":"SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning","created":"2025-05-05","cited_by_count":6,"area":"alignment"},{"id":"2310.15477","title":"CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model","created":"2023-10-24","cited_by_count":5,"area":"alignment"},{"id":"2405.20053","title":"Would I Lie To You? Inference Time Alignment of Language Models using Direct Preference Heads","created":"2024-05-30","cited_by_count":5,"area":"alignment"},{"id":"2411.02442","title":"TODO: Enhancing LLM Alignment with Ternary Preferences","created":"2024-11-02","cited_by_count":5,"area":"alignment"},{"id":"2505.12435","title":"SGDPO: Self-Guided Direct Preference Optimization for Language Model Alignment","created":"2025-05-18","cited_by_count":3,"area":"alignment"},{"id":"2412.00074","title":"Safe to Serve: Aligning Instruction-Tuned Models for Safety and Helpfulness","created":"2024-11-26","cited_by_count":2,"area":"alignment"},{"id":"2507.07723","title":"Stable Preference Optimization: A Bilevel Approach to Catastrophic Preference Shift","created":"2025-07-10","cited_by_count":2,"area":"alignment"},{"id":"2603.08104","title":"Invisible Safety Threat: Malicious Finetuning for LLM via Steganography","created":"2026-03-09","cited_by_count":2,"area":"alignment"},{"id":"2505.13257","title":"Is Active Persona Inference Necessary for Aligning Small Models to Personal Preferences?","created":"2025-05-19","cited_by_count":1,"area":"alignment"},{"id":"2505.23761","title":"Differential Information Distribution: A Bayesian Perspective on Direct Preference Optimization","created":"2025-05-29","cited_by_count":1,"area":"alignment"},{"id":"2510.22881","title":"Offline Preference Optimization via Maximum Marginal Likelihood Estimation","created":"2025-10-27","cited_by_count":1,"area":"alignment"},{"id":"2603.13359","title":"From Refusal Tokens to Refusal Control: Discovering and Steering Category-Specific Refusal Directions","created":"2026-03-09","cited_by_count":1,"area":"alignment"},{"id":"2603.29123","title":"Learning Concepts, Not Tokens: Self-Supervised Semantic Alignment for Language Models","created":"2026-03-31","cited_by_count":1,"area":"alignment"},{"id":"2606.19168","title":"Beyond Safe Data: Pretraining-Stage Alignment with Regular Safety Reflection","created":"2026-06-17","cited_by_count":1,"area":"alignment"},{"id":"2404.06390","title":"Latent Distance Guided Alignment Training for Large Language Models","created":"2024-04-09","cited_by_count":0,"area":"alignment"},{"id":"2505.10775","title":"A Systematic Analysis of Base Model Choice for Reward Modeling","created":"2025-05-16","cited_by_count":0,"area":"alignment"},{"id":"2603.16622","title":"Domain Mixture Design via Log-Likelihood Differences for Aligning Language Models with a Target Model","created":"2026-03-17","cited_by_count":0,"area":"alignment"},{"id":"2604.02574","title":"Understanding the Effects of Safety Unalignment on Large Language Models","created":"2026-04-02","cited_by_count":0,"area":"alignment"},{"id":"2604.02766","title":"Random Is Hard to Beat: Active Selection in online DPO with Modern LLMs","created":"2026-04-03","cited_by_count":0,"area":"alignment"},{"id":"2604.07754","title":"The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training","created":"2026-04-09","cited_by_count":0,"area":"alignment"},{"id":"2605.28597","title":"Position: Retire the \"Positive Backdoor\" Label -- Secret Alignment Requires Strict and Systematic Evaluation","created":"2026-05-27","cited_by_count":0,"area":"alignment"},{"id":"2609.04714","title":"Refuse without Refusal: A Structural Analysis of Safety-Tuning Responses for Reducing False Refusals in Language Models","created":"2026-09-04","cited_by_count":0,"area":"alignment"},{"id":"2609.35201","title":"From Normative Frameworks to Alignment Data: Constructing and Evaluating SFT and Preference Data","created":"2026-09-28","cited_by_count":0,"area":"alignment"}],"next_cursor":null}