{"total":23,"rows":[{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836,"area":"alignment"},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247,"area":"alignment"},{"id":"2302.07459","title":"The Capacity for Moral Self-Correction in Large Language Models","created":"2023-02-15","cited_by_count":173,"area":"alignment"},{"id":"2408.02666","title":"Self-Taught Evaluators","created":"2024-08-05","cited_by_count":72,"area":"alignment"},{"id":"2311.08685","title":"Safer-Instruct: Aligning Language Models with Automated Preference Data","created":"2023-11-15","cited_by_count":27,"area":"alignment"},{"id":"2409.18786","title":"A Survey on the Honesty of Large Language Models","created":"2024-09-27","cited_by_count":23,"area":"alignment"},{"id":"2409.02795","title":"Towards a Unified View of Preference Learning for Large Language Models: A Survey","created":"2024-09-04","cited_by_count":17,"area":"alignment"},{"id":"2508.06249","title":"In-Training Defenses against Emergent Misalignment in Language Models","created":"2025-08-08","cited_by_count":15,"area":"alignment"},{"id":"2505.11166","title":"SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization","created":"2025-05-16","cited_by_count":10,"area":"alignment"},{"id":"2305.06176","title":"Fine-tuning Language Models with Generative Adversarial Reward Modelling","created":"2023-05-09","cited_by_count":8,"area":"alignment"},{"id":"2509.23873","title":"Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning","created":"2025-09-28","cited_by_count":8,"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":"2508.17184","title":"Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Models","created":"2025-08-24","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":"2402.18284","title":"Is Crowdsourcing Breaking Your Bank? Cost-Effective Fine-Tuning of Pre-trained Language Models with Proximal Policy Optimization","created":"2024-02-28","cited_by_count":2,"area":"alignment"},{"id":"2507.06221","title":"Aligned Textual Scoring Rules","created":"2025-07-08","cited_by_count":2,"area":"alignment"},{"id":"2507.21406","title":"Shapley Uncertainty in Natural Language Generation","created":"2025-07-29","cited_by_count":2,"area":"alignment"},{"id":"2510.14400","title":"MedTrust-RAG: Evidence Verification and Trust Alignment for Biomedical Question Answering","created":"2025-10-16","cited_by_count":2,"area":"alignment"},{"id":"2412.11707","title":"Context Filtering with Reward Modeling in Question Answering","created":"2024-12-16","cited_by_count":1,"area":"alignment"},{"id":"2511.06942","title":"HLPD: Aligning LLMs to Human Language Preference for Machine-Revised Text Detection","created":"2025-11-10","cited_by_count":1,"area":"alignment"},{"id":"2601.03401","title":"Rendering Data Unlearnable by Exploiting LLM Alignment Mechanisms","created":"2026-01-06","cited_by_count":1,"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":"2606.13227","title":"PolyAlign: Conditional Human-Distribution Alignment","created":"2026-06-11","cited_by_count":0,"area":"alignment"}],"next_cursor":null}