conftrace_

← Learning Types

Deep Learning › Learning Types ›

Reinforcement Learning from Human Feedback

119 papers

Papers per year

1

1

2

40

46

29

Papers

DecIF: Improving Instruction-Following through Decomposition ACL 2026

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF ACL 2026

SDiaReward: Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness ACL 2026

PAM: Enhancing General Alignment of Large Reasoning Models through Priority-Aware Metacognition ACL 2026

Beyond Pedagogical Principles: Multi-Horizon Preference Optimization for Efficient Socratic Tutoring ACL 2026

C2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences ACL 2026

PRISM: Probabilistic Reward Model with Inherent Structural Modeling ACL 2026

Omni-RewardBench: Toward a Comprehensive Evaluation of Generative Reward Models Across Modalities ACL 2026

Iterative Dual-Model Alignment for Story Evaluation ACL 2026

OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment ACL 2026

Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards ACL 2026

Learning What Matters: Dynamic Dimension Selection and Aggregation for Interpretable Vision-Language Reward Modeling ACL 2026

PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling ACL 2026

Aligning Large Language Models via Fully Self-Synthetic Data ACL 2026

From Individual to Common: An Early Exploration of Consensus in Non-verifiable Data for Balanced Preference Optimization ACL 2026

CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards ACL 2026

DARM: Distribution-Aware Reward Modeling by Alleviating Biases from Low Preference-Context Dependency Data ACL 2026

Edit-Aware Reward Modeling for Chinese Grammatical Error Correction ACL 2026

Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models ACL 2026

ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System ACL 2026

P-Check: Advancing Personalized Reward Model via Learning to Generate Dynamic Checklist ACL 2026

Reward Alignment Optimization: A Direct Point-wise Alignment Approach ACL 2026

PRISMA: Preference-Reinforced Self-Training Approach for Interpretable Emotionally Intelligent Negotiation Dialogues ACL 2026

Self-Guided Alignment: Adaptive Preference Sensing for Multi-Objective Generation ACL 2026

SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility ACL 2026