{"total":38,"rows":[{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2312.09244","title":"Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking","created":"2023-12-14","cited_by_count":200,"area":"alignment"},{"id":"2301.01392","title":"Benchmarks and Algorithms for Offline Preference-Based Reward Learning","created":"2023-01-03","cited_by_count":56,"area":"alignment"},{"id":"2401.00243","title":"Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles","created":"2023-12-30","cited_by_count":56,"area":"alignment"},{"id":"2203.07472","title":"Uncertainty Estimation for Language Reward Models","created":"2022-03-14","cited_by_count":37,"area":"alignment"},{"id":"2402.15062","title":"Don't Just Say \"I don't know\"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanations","created":"2024-02-23","cited_by_count":30,"area":"alignment"},{"id":"2406.00654","title":"Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback","created":"2024-06-02","cited_by_count":20,"area":"alignment"},{"id":"2312.00267","title":"Sample Efficient Preference Alignment in LLMs via Active Exploration","created":"2023-12-01","cited_by_count":18,"area":"alignment"},{"id":"2410.11236","title":"Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling","created":"2024-10-15","cited_by_count":14,"area":"alignment"},{"id":"2406.04854","title":"Uncertainty Aware Learning for Language Model Alignment","created":"2024-06-07","cited_by_count":13,"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":"2510.20369","title":"Ask a Strong LLM Judge when Your Reward Model is Uncertain","created":"2025-10-23","cited_by_count":13,"area":"alignment"},{"id":"2412.08812","title":"Test-Time Alignment via Hypothesis Reweighting","created":"2024-12-11","cited_by_count":11,"area":"alignment"},{"id":"2410.23726","title":"Towards Reliable Alignment: Uncertainty-aware RLHF","created":"2024-10-31","cited_by_count":7,"area":"alignment"},{"id":"2408.07772","title":"Out-of-Distribution Learning with Human Feedback","created":"2024-08-14","cited_by_count":6,"area":"alignment"},{"id":"2409.11212","title":"Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization","created":"2024-09-17","cited_by_count":6,"area":"alignment"},{"id":"2501.17295","title":"Mitigating Hallucinated Translations in Large Language Models with Hallucination-focused Preference Optimization","created":"2025-01-28","cited_by_count":6,"area":"alignment"},{"id":"2606.19818","title":"Uncertainty-Aware Reward Modeling for Stable RLHF","created":"2026-06-18","cited_by_count":6,"area":"alignment"},{"id":"2502.19941","title":"Alleviating Distribution Shift in Synthetic Data for Machine Translation Quality Estimation","created":"2025-02-27","cited_by_count":4,"area":"alignment"},{"id":"2508.18142","title":"Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation","created":"2025-08-25","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":"2602.24040","title":"RewardUQ: A Unified Framework for Uncertainty-Aware Reward Models","created":"2026-02-27","cited_by_count":3,"area":"alignment"},{"id":"2606.21795","title":"Discretizing Reward Models","created":"2026-06-19","cited_by_count":3,"area":"alignment"},{"id":"2503.12528","title":"Investigating Human-Aligned Large Language Model Uncertainty","created":"2025-03-16","cited_by_count":2,"area":"alignment"},{"id":"2507.05179","title":"From Fragments to Facts: A Curriculum-Driven DPO Approach for Generating Hindi News Veracity Explanations","created":"2025-07-07","cited_by_count":2,"area":"alignment"},{"id":"2511.09864","title":"Uncertainty-Guided Checkpoint Selection for Reinforcement Finetuning of Large Language Models","created":"2025-11-13","cited_by_count":2,"area":"alignment"},{"id":"2511.20668","title":"PIRA: Preference-Oriented Instruction-Tuned Reward Models with Dual Aggregation","created":"2025-11-14","cited_by_count":1,"area":"alignment"},{"id":"2604.26360","title":"Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking","created":"2026-04-29","cited_by_count":1,"area":"alignment"},{"id":"2605.13536","title":"HLS-Seek: QoR-Aware Code Generation for High-Level Synthesis via Proxy Comparative Reward Reinforcement Learning","created":"2026-05-13","cited_by_count":1,"area":"alignment"},{"id":"2602.02451","title":"Active Causal Experimentalist (ACE): Learning Intervention Strategies via Direct Preference Optimization","created":"2026-02-02","cited_by_count":0,"area":"alignment"},{"id":"2603.08145","title":"DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding","created":"2026-03-09","cited_by_count":0,"area":"alignment"},{"id":"2603.22922","title":"Quality Over Clicks: Iterative Reinforcement Learning for Early-Stage E-Commerce Query Suggestion","created":"2026-03-24","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":"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":"2607.14480","title":"Lower-Resource, Higher Scores: Language Bias in LLM Evaluators","created":"2026-07-16","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":"2609.34506","title":"Does Model Uncertainty Track Human Ambiguity? Evidence from Multi-Annotator Vision Benchmarks","created":"2026-09-28","cited_by_count":0,"area":"alignment"}],"next_cursor":null}