{"total":56,"rows":[{"id":"2403.19159","title":"Disentangling Length from Quality in Direct Preference Optimization","created":"2024-03-28","cited_by_count":196,"area":"alignment"},{"id":"2406.02900","title":"Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms","created":"2024-06-05","cited_by_count":143,"area":"alignment"},{"id":"2402.09345","title":"InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling","created":"2024-02-14","cited_by_count":79,"area":"alignment"},{"id":"2405.19316","title":"Robust Preference Optimization through Reward Model Distillation","created":"2024-05-29","cited_by_count":67,"area":"alignment"},{"id":"2407.11046","title":"A Survey on LoRA of Large Language Models","created":"2024-07-08","cited_by_count":67,"area":null},{"id":"2407.06089","title":"Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models","created":"2024-07-08","cited_by_count":44,"area":null},{"id":"2408.10215","title":"Comprehensive Overview of Reward Engineering and Shaping in Advancing Reinforcement Learning Applications","created":"2024-07-22","cited_by_count":38,"area":"deeprl"},{"id":"2402.12264","title":"Uncertainty quantification in fine-tuned LLMs using LoRA ensembles","created":"2024-02-19","cited_by_count":37,"area":null},{"id":"2402.13210","title":"Bayesian Reward Models for LLM Alignment","created":"2024-02-20","cited_by_count":35,"area":"alignment"},{"id":"2403.05171","title":"Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation","created":"2024-03-08","cited_by_count":33,"area":"alignment"},{"id":"2409.15360","title":"Reward-Robust RLHF in LLMs","created":"2024-09-18","cited_by_count":32,"area":"alignment"},{"id":"2406.10957","title":"Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence","created":"2024-06-16","cited_by_count":31,"area":"alignment"},{"id":"2409.17407","title":"Post-hoc Reward Calibration: A Case Study on Length Bias","created":"2024-09-25","cited_by_count":29,"area":"alignment"},{"id":"2402.00742","title":"Transforming and Combining Rewards for Aligning Large Language Models","created":"2024-02-01","cited_by_count":25,"area":"alignment"},{"id":"2403.15115","title":"Language Models in Dialogue: Conversational Maxims for Human-AI Interactions","created":"2024-03-22","cited_by_count":21,"area":null},{"id":"2501.19358","title":"The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking","created":"2025-01-31","cited_by_count":18,"area":"alignment"},{"id":"2504.06141","title":"Adversarial Training of Reward Models","created":"2025-04-08","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":"2403.01197","title":"DMoERM: Recipes of Mixture-of-Experts for Effective Reward Modeling","created":"2024-03-02","cited_by_count":15,"area":"alignment"},{"id":"2409.02976","title":"Hallucination Detection in LLMs: Fast and Memory-Efficient Fine-Tuned Models","created":"2024-09-04","cited_by_count":15,"area":null},{"id":"2412.09544","title":"Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking","created":"2024-12-12","cited_by_count":13,"area":"alignment"},{"id":"2505.07271","title":"On the Robustness of Reward Models for Language Model Alignment","created":"2025-05-12","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":"2601.22664","title":"Real-Time Aligned Reward Model beyond Semantics","created":"2026-01-30","cited_by_count":13,"area":"alignment"},{"id":"2503.13505","title":"Ensemble Learning for Large Language Models in Text and Code Generation: A Survey","created":"2025-03-13","cited_by_count":9,"area":null},{"id":"2410.11677","title":"Understanding Likelihood Over-optimisation in Direct Alignment Algorithms","created":"2024-10-15","cited_by_count":7,"area":"alignment"},{"id":"2410.23726","title":"Towards Reliable Alignment: Uncertainty-aware RLHF","created":"2024-10-31","cited_by_count":7,"area":"alignment"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2405.06424","title":"Improving Instruction Following in Language Models through Proxy-Based Uncertainty Estimation","created":"2024-05-10","cited_by_count":6,"area":null},{"id":"2410.06431","title":"Functional-level Uncertainty Quantification for Calibrated Fine-tuning on LLMs","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2410.20187","title":"Uncertainty-Penalized Direct Preference Optimization","created":"2024-10-26","cited_by_count":6,"area":"alignment"},{"id":"2505.10597","title":"Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment","created":"2025-05-15","cited_by_count":6,"area":"alignment"},{"id":"2505.23316","title":"Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPO","created":"2025-05-29","cited_by_count":5,"area":"alignment"},{"id":"2510.13694","title":"Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking","created":"2025-10-15","cited_by_count":5,"area":"alignment"},{"id":"2504.13134","title":"Energy-Based Reward Models for Robust Language Model Alignment","created":"2025-04-17","cited_by_count":4,"area":"alignment"},{"id":"2511.08968","title":"Bayesian Mixture of Experts For Large Language Models","created":"2025-11-12","cited_by_count":4,"area":"moe"},{"id":"2602.24040","title":"RewardUQ: A Unified Framework for Uncertainty-Aware Reward Models","created":"2026-02-27","cited_by_count":3,"area":"alignment"},{"id":"2604.04648","title":"From Curiosity to Caution: Mitigating Reward Hacking for Best-of-N with Pessimism","created":"2026-04-06","cited_by_count":3,"area":"lr"},{"id":"2410.09908","title":"Beyond Adapter Retrieval: Latent Geometry-Preserving Composition via Sparse Task Projection","created":"2024-10-13","cited_by_count":2,"area":null},{"id":"2602.11351","title":"Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization","created":"2026-02-11","cited_by_count":2,"area":"agents"},{"id":"2505.21478","title":"Policy Optimized Text-to-Image Pipeline Design","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2510.05526","title":"Provably Mitigating Corruption, Overoptimization, and Verbosity Simultaneously in Offline and Online RLHF/DPO Alignment","created":"2025-10-07","cited_by_count":1,"area":"alignment"},{"id":"2606.09073","title":"A Unifying Lens on Reward Uncertainty in RLHF","created":"2026-06-08","cited_by_count":1,"area":"alignment"},{"id":"2609.19164","title":"Advantage Scale Calibration Imbalance in Group-Relative Optimization under Low-Variance Rewards: Diagnosis and Bounded Recovery","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2405.14103","title":"Online Self-Preferring Language Models","created":"2024-05-23","cited_by_count":0,"area":"alignment"},{"id":"2507.15906","title":"Towards Reliable, Uncertainty-Aware Alignment","created":"2025-07-21","cited_by_count":0,"area":"alignment"},{"id":"2512.20884","title":"The Silent Scholar Problem: A Probabilistic Framework for Breaking Epistemic Asymmetry in LLM Agents","created":"2025-12-24","cited_by_count":0,"area":"rag"},{"id":"2605.00155","title":"Wasserstein Distributionally Robust Regret Optimization for Reinforcement Learning from Human Feedback","created":"2026-04-30","cited_by_count":0,"area":"alignment"},{"id":"2605.11328","title":"Epistemic Uncertainty for Test-Time Discovery","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2606.22402","title":"Reinforcement learning to improve large language model-based automated code compliance systems","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2609.06893","title":"Towards Bridging the Gap Between Offline and Iterative Alignment via Preference Distillation","created":"2026-09-07","cited_by_count":0,"area":"alignment"},{"id":"2609.33221","title":"RMB: Reward Model Boosting Mitigates Reward Hacking","created":"2026-09-27","cited_by_count":0,"area":"alignment"},{"id":"2609.33426","title":"TeacherGRPO: Closing the Capacity Gap in Reasoning Distillation via Teacher Alignment","created":"2026-09-27","cited_by_count":0,"area":"distill"},{"id":"2609.36900","title":"STAR-GRPO: Canonical Anchoring and Reliability-First Advantages against Representation-Dependent Reward Hacking","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.07109","title":"JudgeMoE: Distributional Aggregation for LLM-as-a-Judge","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.11281","title":"How to post-train on a surrogate: Envelope sampling mitigates reward hacking","created":"2026-10-08","cited_by_count":0,"area":"alignment"}],"next_cursor":null}