{"total":21,"rows":[{"id":"2403.16950","title":"Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators","created":"2024-03-25","cited_by_count":149,"area":"alignment"},{"id":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96,"area":"alignment"},{"id":"2403.05612","title":"Unfamiliar Finetuning Examples Control How Language Models Hallucinate","created":"2024-03-08","cited_by_count":87,"area":"alignment"},{"id":"2409.13156","title":"RRM: Robust Reward Model Training Mitigates Reward Hacking","created":"2024-09-20","cited_by_count":76,"area":"alignment"},{"id":"2406.11370","title":"Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments","created":"2024-06-17","cited_by_count":25,"area":"alignment"},{"id":"2505.01997","title":"Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach","created":"2025-05-04","cited_by_count":25,"area":"alignment"},{"id":"2406.13173","title":"Biomedical Visual Instruction Tuning with Clinician Preference Alignment","created":"2024-06-19","cited_by_count":21,"area":"alignment"},{"id":"2402.00667","title":"Improving Weak-to-Strong Generalization with Scalable Oversight and Ensemble Learning","created":"2024-02-01","cited_by_count":18,"area":"alignment"},{"id":"2210.07652","title":"Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values","created":"2022-10-14","cited_by_count":13,"area":"alignment"},{"id":"2503.09025","title":"Aligning to What? Limits to RLHF Based Alignment","created":"2025-03-12","cited_by_count":8,"area":"alignment"},{"id":"2502.01925","title":"PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling","created":"2025-02-04","cited_by_count":6,"area":"alignment"},{"id":"2504.09895","title":"Learning from Reference Answers: Versatile Language Model Alignment without Binary Human Preference Data","created":"2025-04-14","cited_by_count":4,"area":"alignment"},{"id":"2510.00263","title":"Judging with Confidence: Calibrating Autoraters to Preference Distributions","created":"2025-09-30","cited_by_count":3,"area":"alignment"},{"id":"2508.06124","title":"AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models","created":"2025-08-08","cited_by_count":2,"area":"alignment"},{"id":"2603.10243","title":"GR-SAP: Generative Replay for Safety Alignment Preservation during Fine-Tuning","created":"2026-03-10","cited_by_count":2,"area":"alignment"},{"id":"2604.02174","title":"Quantifying Self-Preservation Bias in Large Language Models","created":"2026-04-02","cited_by_count":2,"area":"alignment"},{"id":"2604.17237","title":"HeadRank: Decoding-Free Passage Reranking via Preference-Aligned Attention Heads","created":"2026-04-19","cited_by_count":2,"area":"alignment"},{"id":"2512.11998","title":"Direct Confidence Alignment: Aligning Verbalized Confidence with Internal Confidence In Large Language Models","created":"2025-12-12","cited_by_count":1,"area":"alignment"},{"id":"2406.14208","title":"SeCoKD: Aligning Large Language Models for In-Context Learning with Fewer Shots","created":"2024-06-20","cited_by_count":0,"area":"alignment"},{"id":"2509.24189","title":"SPECTRA: Revealing the Full Spectrum of User Preferences via Distributional LLM Inference","created":"2025-09-29","cited_by_count":0,"area":"alignment"},{"id":"2606.24004","title":"Towards Spec Learning: Inference-Time Alignment from Preference Pairs","created":"2026-06-22","cited_by_count":0,"area":"alignment"}],"next_cursor":null}