{"total":60,"rows":[{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720,"area":"alignment"},{"id":"2305.14975","title":"Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback","created":"2023-05-24","cited_by_count":812,"area":"alignment"},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2309.16240","title":"Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints","created":"2023-09-28","cited_by_count":174,"area":"alignment"},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2410.09724","title":"Taming Overconfidence in LLMs: Reward Calibration in RLHF","created":"2024-10-13","cited_by_count":112,"area":"alignment"},{"id":"2406.18853","title":"Decoding-Time Language Model Alignment with Multiple Objectives","created":"2024-06-27","cited_by_count":94,"area":"alignment"},{"id":"2402.09267","title":"Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation","created":"2024-02-14","cited_by_count":80,"area":"alignment"},{"id":"2409.19817","title":"Calibrating Language Models with Adaptive Temperature Scaling","created":"2024-09-29","cited_by_count":58,"area":"alignment"},{"id":"2412.14516","title":"Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment","created":"2024-12-19","cited_by_count":51,"area":"alignment"},{"id":"2404.02655","title":"Calibrating the Confidence of Large Language Models by Eliciting Fidelity","created":"2024-04-03","cited_by_count":47,"area":"alignment"},{"id":"2309.16155","title":"The Trickle-down Impact of Reward (In-)consistency on RLHF","created":"2023-09-28","cited_by_count":29,"area":"alignment"},{"id":"2312.07401","title":"On Diversified Preferences of Large Language Model Alignment","created":"2023-12-12","cited_by_count":26,"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":"2305.17608","title":"Reward Collapse in Aligning Large Language Models","created":"2023-05-28","cited_by_count":24,"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":"2409.18786","title":"A Survey on the Honesty of Large Language Models","created":"2024-09-27","cited_by_count":23,"area":"alignment"},{"id":"2409.09603","title":"Towards Data-Centric RLHF: Simple Metrics for Preference Dataset Comparison","created":"2024-09-15","cited_by_count":21,"area":"alignment"},{"id":"2310.11732","title":"Investigating Uncertainty Calibration of Aligned Language Models under the Multiple-Choice Setting","created":"2023-10-18","cited_by_count":20,"area":"alignment"},{"id":"2406.02764","title":"Adaptive Preference Scaling for Reinforcement Learning with Human Feedback","created":"2024-06-04","cited_by_count":20,"area":"alignment"},{"id":"2311.14743","title":"A Baseline Analysis of Reward Models' Ability To Accurately Analyze Foundation Models Under Distribution Shift","created":"2023-11-21","cited_by_count":18,"area":"alignment"},{"id":"2412.11803","title":"UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models","created":"2024-12-16","cited_by_count":13,"area":"alignment"},{"id":"2505.10892","title":"Multi-Objective Preference Optimization: Improving Human Alignment of Generative Models","created":"2025-05-16","cited_by_count":13,"area":"alignment"},{"id":"2510.17426","title":"Navigating the Alignment-Calibration Trade-off: A Pareto-Superior Frontier via Model Merging","created":"2025-10-20","cited_by_count":10,"area":"alignment"},{"id":"2410.11055","title":"Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only","created":"2024-10-14","cited_by_count":9,"area":"alignment"},{"id":"2508.15811","title":"From Clicks to Preference: A Multi-stage Alignment Framework for Generative Query Suggestion in Conversational System","created":"2025-08-15","cited_by_count":9,"area":"alignment"},{"id":"2502.13177","title":"KL Penalty Control via Perturbation for Direct Preference Optimization","created":"2025-02-18","cited_by_count":5,"area":"alignment"},{"id":"2605.09702","title":"Calibrate, Don't Curate: Label-Efficient Estimation from Noisy LLM Judges","created":"2026-05-10","cited_by_count":5,"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":"2507.18417","title":"FinDPO: Financial Sentiment Analysis for Algorithmic Trading through Preference Optimization of LLMs","created":"2025-07-24","cited_by_count":4,"area":"alignment"},{"id":"2601.23096","title":"CATTO: Balancing Preferences and Confidence in Language Models","created":"2026-01-30","cited_by_count":4,"area":"alignment"},{"id":"2603.24124","title":"The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimation","created":"2026-03-25","cited_by_count":4,"area":"alignment"},{"id":"2606.17006","title":"TuneJury: An Open Metric for Improving Music Generation Preference Alignment","created":"2026-06-15","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":"2602.08829","title":"WildReward: Learning Reward Models from In-the-Wild Human Interactions","created":"2026-02-09","cited_by_count":3,"area":"alignment"},{"id":"2602.20670","title":"CAMEL: Confidence-Gated Reflection for Reward Modeling","created":"2026-02-24","cited_by_count":3,"area":"alignment"},{"id":"2602.24040","title":"RewardUQ: A Unified Framework for Uncertainty-Aware Reward Models","created":"2026-02-27","cited_by_count":3,"area":"alignment"},{"id":"2604.10585","title":"Calibration Collapse Under Sycophancy Fine-Tuning: How Reward Hacking Breaks Uncertainty Quantification in LLMs","created":"2026-04-12","cited_by_count":3,"area":"alignment"},{"id":"2509.25509","title":"Can Molecular Foundation Models Know What They Don't Know? A Simple Remedy with Preference Optimization","created":"2025-09-29","cited_by_count":2,"area":"alignment"},{"id":"2607.03528","title":"Aligning Language Models with Selective Prediction","created":"2026-07-03","cited_by_count":2,"area":"alignment"},{"id":"2608.19802","title":"Stopping and Routing LLM Judge Panels","created":"2026-08-20","cited_by_count":2,"area":"alignment"},{"id":"2409.13919","title":"Measuring Error Alignment for Decision-Making Systems","created":"2024-09-20","cited_by_count":1,"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":"2604.00997","title":"Uncertainty-Aware Variational Reward Factorization via Probabilistic Preference Bases for LLM Personalization","created":"2026-04-01","cited_by_count":1,"area":"alignment"},{"id":"2607.07023","title":"Online Data Selection Is Implicit Alignment","created":"2026-07-08","cited_by_count":1,"area":"alignment"},{"id":"2505.15626","title":"Direct Preference Optimization for Adaptive Concept-based Explanations","created":"2025-05-21","cited_by_count":0,"area":"alignment"},{"id":"2512.17956","title":"Victor Calibration (VC): Multi-Pass Confidence Calibration and CP4.3 Governance Stress Test under Round-Table Orchestration","created":"2025-12-18","cited_by_count":0,"area":"alignment"},{"id":"2602.00619","title":"Jailbreaking LLMs via Calibration","created":"2026-01-31","cited_by_count":0,"area":"alignment"},{"id":"2604.14651","title":"CURA: Clinical Uncertainty Risk Alignment for Language Model-Based Risk Prediction","created":"2026-04-16","cited_by_count":0,"area":"alignment"},{"id":"2605.10843","title":"Training-Free Cultural Alignment of Large Language Models via Persona Disagreement","created":"2026-05-11","cited_by_count":0,"area":"alignment"},{"id":"2605.12406","title":"Semantic Reward Collapse and the Preservation of Epistemic Integrity in Adaptive AI Systems","created":"2026-05-12","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":"2605.30487","title":"Configurable Reward Model for Balanced Safety Alignment","created":"2026-05-28","cited_by_count":0,"area":"alignment"},{"id":"2606.03238","title":"When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming","created":"2026-06-02","cited_by_count":0,"area":"alignment"},{"id":"2607.07859","title":"Feedback Manipulation Regularization: Enabling Offline Agent Alignment for Imitation Learning","created":"2026-07-08","cited_by_count":0,"area":"alignment"},{"id":"2609.00624","title":"Trust Your Guide Only When Certain: Uncertainty-Aware Sparse Alignment at Inference Time","created":"2026-09-01","cited_by_count":0,"area":"alignment"},{"id":"2609.04066","title":"Subspace Inference Enables Efficient Active Reward Learning from Preferences","created":"2026-09-03","cited_by_count":0,"area":"alignment"},{"id":"2609.32617","title":"The Alignment Paradox: How Post-Training Amplifies Confident Hallucinations in Language Models","created":"2026-09-26","cited_by_count":0,"area":"alignment"},{"id":"2609.38647","title":"Uncertainty-Normalized Margins for Direct Preference Optimization","created":"2026-09-29","cited_by_count":0,"area":"alignment"},{"id":"2610.20350","title":"Lifted State Policy Optimization: Internalizing Self-Correction through Transition Geometry","created":"2026-10-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}