Cover Image

When Right Meets Wrong: Bilateral Context Conditioning with Reward-Confidence Correction for GRPO

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Yu, Lan, Tian, Qi, Zhengling
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

InSPO: Unlocking Intrinsic Self-Reflection for LLM Preference Optimization
by: Li, Yu, et al.
Published: (2025)

ARISE: Agent Reasoning with Intrinsic Skill Evolution in Hierarchical Reinforcement Learning
by: Li, Yu, et al.
Published: (2026)

OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning
by: Li, Yu, et al.
Published: (2026)

The Confidence Paradox: Can LLM Know When It's Wrong
by: Tripathi, Sahil, et al.
Published: (2025)

Robust Offline Reinforcement learning with Heavy-Tailed Rewards
by: Zhu, Jin, et al.
Published: (2023)

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity
by: Zhang, Xingjian, et al.
Published: (2025)

GRPO is Secretly a Process Reward Model
by: Sullivan, Michael, et al.
Published: (2025)

Confidence as a Reward: Transforming LLMs into Reward Models
by: Du, He, et al.
Published: (2025)

GRPO and Reflection Reward for Mathematical Reasoning in Large Language Models
by: Wang, Zhijie
Published: (2026)

ShapE-GRPO: Shapley-Enhanced Reward Allocation for Multi-Candidate LLM Training
by: Ai, Rui, et al.
Published: (2026)

RC-GRPO: Reward-Conditioned Group Relative Policy Optimization for Multi-Turn Tool Calling Agents
by: Zhong, Haitian, et al.
Published: (2026)

Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident, Especially When They are Wrong
by: Fu, Tairan, et al.
Published: (2025)

Boosting In-Context Learning in LLMs Through the Lens of Classical Supervised Learning
by: Gundem, Korel, et al.
Published: (2025)

Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict
by: Chen, Yihang, et al.
Published: (2026)

CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards
by: Tian, Wei, et al.
Published: (2026)

Stable but Wrong: When More Data Degrades Scientific Conclusions
by: Zhang, Zhipeng, et al.
Published: (2026)

What's Wrong? Refining Meeting Summaries with LLM Feedback
by: Kirstein, Frederic, et al.
Published: (2024)

Noise-corrected GRPO: From Noisy Rewards to Unbiased Gradients
by: Mansouri, Omar El, et al.
Published: (2025)

Seeing Right but Saying Wrong: Inter- and Intra-Layer Refinement in MLLMs without Training
by: Song, Shezheng, et al.
Published: (2026)

MMR-GRPO: Accelerating GRPO-Style Training through Diversity-Aware Reward Reweighting
by: Wei, Kangda, et al.
Published: (2026)

Right Prediction, Wrong Reasoning: Uncovering LLM Misalignment in RA Disease Diagnosis
by: Maharana, Umakanta, et al.
Published: (2025)

Shaping Explanations: Semantic Reward Modeling with Encoder-Only Transformers for GRPO
by: Pappone, Francesco, et al.
Published: (2025)

GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy Entropy
by: Tan, Hongze, et al.
Published: (2025)

Bridging the Semantic Gap: Contrastive Rewards for Multilingual Text-to-SQL with GRPO
by: Kattamuri, Ashish, et al.
Published: (2025)

Beyond Correctness: Confidence-Aware Reward Modeling for Enhancing Large Language Model Reasoning
by: He, Qianxi, et al.
Published: (2025)

Perplexity Cannot Always Tell Right from Wrong
by: Veličković, Petar, et al.
Published: (2026)

PACR: Progressively Ascending Confidence Reward for LLM Reasoning
by: Yoon, Eunseop, et al.
Published: (2025)

Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?
by: Wen, Xueru, et al.
Published: (2024)

When the Majority is Wrong: Modeling Annotator Disagreement for Subjective Tasks
by: Fleisig, Eve, et al.
Published: (2023)

OffTopicEval: When Large Language Models Enter the Wrong Chat, Almost Always!
by: Lei, Jingdi, et al.
Published: (2025)

Rethinking the Unsolvable: When In-Context Search Meets Test-Time Scaling
by: Xia, Fanzeng, et al.
Published: (2025)

TIGFlow-GRPO: Trajectory Forecasting via Interaction-Aware Flow Matching and Reward-Guided Optimization
by: Jing, Xuepeng, et al.
Published: (2026)

Agentic Trading: When LLM Agents Meet Financial Markets
by: Xia, Yihan, et al.
Published: (2026)

Decoupling Spatio-Temporal Prediction: When Lightweight Large Models Meet Adaptive Hypergraphs
by: Chen, Jiawen, et al.
Published: (2025)

BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion Models
by: Li, Yuming, et al.
Published: (2025)

CAMEL: Confidence-Gated Reflection for Reward Modeling
by: Zhu, Zirui, et al.
Published: (2026)

CoRPO: Adding a Correctness Bias to GRPO Improves Generalization
by: Garg, Anisha, et al.
Published: (2025)

SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization
by: Chen, Minghan, et al.
Published: (2025)

Beyond Demand Estimation: Consumer Surplus Evaluation via Cumulative Propensity Weights
by: Bian, Zeyu, et al.
Published: (2026)

Right Looks, Wrong Reasons: Compositional Fidelity in Text-to-Image Generation
by: Vatsa, Mayank, et al.
Published: (2025)