{"total":42,"rows":[{"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":"2310.06387","title":"Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations","created":"2023-10-10","cited_by_count":431,"area":"alignment"},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247,"area":"alignment"},{"id":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231,"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":"2409.18169","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","created":"2024-09-26","cited_by_count":90,"area":"alignment"},{"id":"2408.02666","title":"Self-Taught Evaluators","created":"2024-08-05","cited_by_count":72,"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":"2302.05206","title":"The Wisdom of Hindsight Makes Language Models Better Instruction Followers","created":"2023-02-10","cited_by_count":62,"area":"alignment"},{"id":"2405.13967","title":"Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity","created":"2024-05-22","cited_by_count":35,"area":"alignment"},{"id":"2309.11166","title":"Are Large Language Models Really Robust to Word-Level Perturbations?","created":"2023-09-20","cited_by_count":32,"area":"alignment"},{"id":"2506.03637","title":"RewardAnything: Generalizable Principle-Following Reward Models","created":"2025-06-04","cited_by_count":28,"area":"alignment"},{"id":"2503.11751","title":"reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs","created":"2025-03-14","cited_by_count":25,"area":"alignment"},{"id":"2406.11431","title":"Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization","created":"2024-06-17","cited_by_count":23,"area":"alignment"},{"id":"2505.13388","title":"R3: Robust Rubric-Agnostic Reward Models","created":"2025-05-19","cited_by_count":23,"area":"alignment"},{"id":"2509.11864","title":"NeuroStrike: Neuron-Level Attacks on Aligned LLMs","created":"2025-09-15","cited_by_count":22,"area":"alignment"},{"id":"2302.05721","title":"Synthesizing Human Gaze Feedback for Improved NLP Performance","created":"2023-02-11","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":"2505.18588","title":"Safety Alignment via Constrained Knowledge Unlearning","created":"2025-05-24","cited_by_count":14,"area":"alignment"},{"id":"2502.15435","title":"Single-pass Detection of Jailbreaking Input in Large Language Models","created":"2025-02-21","cited_by_count":10,"area":"alignment"},{"id":"2509.01301","title":"Culture is Everywhere: A Call for Intentionally Cultural Evaluation","created":"2025-09-01","cited_by_count":10,"area":"alignment"},{"id":"2510.01243","title":"Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing","created":"2025-09-24","cited_by_count":10,"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":"2310.16681","title":"BabyStories: Can Reinforcement Learning Teach Baby Language Models to Write Better Stories?","created":"2023-10-25","cited_by_count":7,"area":"alignment"},{"id":"2402.16211","title":"HypoTermQA: Hypothetical Terms Dataset for Benchmarking Hallucination Tendency of LLMs","created":"2024-02-25","cited_by_count":6,"area":"alignment"},{"id":"2311.05374","title":"TencentLLMEval: A Hierarchical Evaluation of Real-World Capabilities for Human-Aligned LLMs","created":"2023-11-09","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":"2411.11853","title":"Chat Bankman-Fried: an Exploration of LLM Alignment in Finance","created":"2024-11-01","cited_by_count":5,"area":"alignment"},{"id":"2510.20449","title":"LM-mixup: Text Data Augmentation via Language Model based Mixup","created":"2025-10-23","cited_by_count":3,"area":"alignment"},{"id":"2511.12464","title":"Probing Preference Representations: A Multi-Dimensional Evaluation and Analysis Method for Reward Models","created":"2025-11-16","cited_by_count":3,"area":"alignment"},{"id":"2405.19763","title":"Enhancing Reinforcement Learning with Label-Sensitive Reward for Natural Language Understanding","created":"2024-05-30","cited_by_count":2,"area":"alignment"},{"id":"2503.23362","title":"Mixture of Routers","created":"2025-03-30","cited_by_count":2,"area":"alignment"},{"id":"2504.08590","title":"Playpen: An Environment for Exploring Learning Through Conversational Interaction","created":"2025-04-11","cited_by_count":2,"area":"alignment"},{"id":"2602.16977","title":"Fail-Closed Alignment for Large Language Models","created":"2026-02-19","cited_by_count":2,"area":"alignment"},{"id":"2603.23091","title":"When Language Models Lose Their Mind: The Consequences of Brain Misalignment","created":"2026-03-24","cited_by_count":2,"area":"alignment"},{"id":"2407.20383","title":"Appraisal-Guided Proximal Policy Optimization: Modeling Psychological Disorders in Dynamic Grid World","created":"2024-07-29","cited_by_count":1,"area":"alignment"},{"id":"2506.13285","title":"DualEdit: Mitigating Safety Fallback in LLM Backdoor Editing via Affirmation-Refusal Regulation","created":"2025-06-16","cited_by_count":1,"area":"alignment"},{"id":"2606.06519","title":"SafeGene: Reusable Adapters for Transferable Safety Alignment","created":"2026-06-02","cited_by_count":1,"area":"alignment"},{"id":"2601.03005","title":"JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification","created":"2026-01-06","cited_by_count":0,"area":"alignment"},{"id":"2605.17458","title":"ClaHF: A Human Feedback-inspired Reinforcement Learning Framework for Improving Classification Tasks","created":"2026-05-17","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":"2608.20554","title":"aiXamine: Unified Black-Box Evaluation of Cross-Dimensional Trade-offs in LLM Safety, Security, and Privacy","created":"2026-08-20","cited_by_count":0,"area":"alignment"}],"next_cursor":null}