{"total":29,"rows":[{"id":"2403.17710","title":"Optimization-based Prompt Injection Attack to LLM-as-a-Judge","created":"2024-03-26","cited_by_count":143,"area":"alignment"},{"id":"2309.12053","title":"AceGPT, Localizing Large Language Models in Arabic","created":"2023-09-21","cited_by_count":75,"area":"alignment"},{"id":"2311.18743","title":"AlignBench: Benchmarking Chinese Alignment of Large Language Models","created":"2023-11-30","cited_by_count":68,"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":"2308.12014","title":"From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models","created":"2023-08-23","cited_by_count":45,"area":"alignment"},{"id":"2311.06025","title":"ChiMed-GPT: A Chinese Medical Large Language Model with Full Training Regime and Better Alignment to Human Preferences","created":"2023-11-10","cited_by_count":43,"area":"alignment"},{"id":"2308.05696","title":"A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment","created":"2023-08-10","cited_by_count":33,"area":"alignment"},{"id":"2307.12966","title":"Aligning Large Language Models with Human: A Survey","created":"2023-07-24","cited_by_count":32,"area":"alignment"},{"id":"2312.15907","title":"Align on the Fly: Adapting Chatbot Behavior to Established Norms","created":"2023-12-26","cited_by_count":23,"area":"alignment"},{"id":"2502.11555","title":"Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models","created":"2025-02-17","cited_by_count":22,"area":"alignment"},{"id":"2504.04950","title":"A Unified Pairwise Framework for RLHF: Bridging Generative Reward Modeling and Policy Optimization","created":"2025-04-07","cited_by_count":21,"area":"alignment"},{"id":"2401.03129","title":"Examining Forgetting in Continual Pre-training of Aligned Large Language Models","created":"2024-01-06","cited_by_count":18,"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":"2403.08309","title":"HRLAIF: Improvements in Helpfulness and Harmlessness in Open-domain Reinforcement Learning From AI Feedback","created":"2024-03-13","cited_by_count":15,"area":"alignment"},{"id":"2407.16637","title":"Course-Correction: Safety Alignment Using Synthetic Preferences","created":"2024-07-23","cited_by_count":13,"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":"2406.10307","title":"What is the best model? Application-driven Evaluation for Large Language Models","created":"2024-06-14","cited_by_count":4,"area":"alignment"},{"id":"2406.12182","title":"Aqulia-Med LLM: Pioneering Full-Process Open-Source Medical Language Models","created":"2024-06-18","cited_by_count":4,"area":"alignment"},{"id":"2408.10642","title":"Minor SFT loss for LLM fine-tune to increase performance and reduce model deviation","created":"2024-08-20","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":"2411.00809","title":"Adaptive Segment-level Reward: Bridging the Gap Between Action and Reward Space in Alignment","created":"2024-10-23","cited_by_count":2,"area":"alignment"},{"id":"2604.16916","title":"When Choices Become Risks: Safety Failures of Large Language Models under Multiple-Choice Constraints","created":"2026-04-18","cited_by_count":2,"area":"alignment"},{"id":"2502.03843","title":"Improving Natural Language Understanding for LLMs via Large-Scale Instruction Synthesis","created":"2025-02-06","cited_by_count":1,"area":"alignment"},{"id":"2509.25148","title":"AAPA: Adversarially Anchored Preference Alignment for Post-Training of Large Language Models","created":"2025-09-29","cited_by_count":1,"area":"alignment"},{"id":"2510.20187","title":"Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values","created":"2025-10-23","cited_by_count":1,"area":"alignment"},{"id":"2507.15275","title":"ChiMed 2.0: Advancing Chinese Medical Dataset in Facilitating Large Language Modeling","created":"2025-07-21","cited_by_count":0,"area":"alignment"},{"id":"2510.15746","title":"LLMs Judge Themselves: A Game-Theoretic Framework for Human-Aligned Evaluation","created":"2025-10-17","cited_by_count":0,"area":"alignment"},{"id":"2607.02914","title":"Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models","created":"2026-07-03","cited_by_count":0,"area":"alignment"},{"id":"2610.04328","title":"Bidirectional Preference Synthesis: Learning Prompt-Conditioned Preferences from Boundary Failures","created":"2026-10-03","cited_by_count":0,"area":"alignment"}],"next_cursor":null}