Copertina

Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ma, Zhengzhao, Wen, Xueru, Cao, Boxi, Lu, Yaojie, Lin, Hongyu, Yang, Jinglin, He, Min, Han, Xianpei, Sun, Le
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards
di: Ren, Mengjie, et al.
Pubblicazione: (2026)

Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models
di: Zheng, Jiasheng, et al.
Pubblicazione: (2024)

P^2O: Joint Policy and Prompt Optimization
di: Lu, Xinyu, et al.
Pubblicazione: (2026)

Coupled Variational Reinforcement Learning for Language Model General Reasoning
di: Wen, Xueru, et al.
Pubblicazione: (2025)

Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering
di: Guan, Xinyan, et al.
Pubblicazione: (2024)

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

Critic-CoT: Boosting the reasoning abilities of large language model via Chain-of-thoughts Critic
di: Zheng, Xin, et al.
Pubblicazione: (2024)

The Life Cycle of Knowledge in Big Language Models: A Survey
di: Cao, Boxi, et al.
Pubblicazione: (2023)

Multi-Facet Counterfactual Learning for Content Quality Evaluation
di: Zheng, Jiasheng, et al.
Pubblicazione: (2024)

Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models
di: Yan, Xinru, et al.
Pubblicazione: (2026)

ScaleBox: Enabling High-Fidelity and Scalable Code Verification for Large Language Models
di: Zheng, Jiasheng, et al.
Pubblicazione: (2026)

Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination
di: Zheng, Jiasheng, et al.
Pubblicazione: (2026)

Memorizing is Not Enough: Deep Knowledge Injection Through Reasoning
di: Xu, Ruoxi, et al.
Pubblicazione: (2025)

When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models
di: Mao, Yingzhi, et al.
Pubblicazione: (2025)

LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents
di: Peng, Xiaoxuan, et al.
Pubblicazione: (2026)

The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models
di: Li, Zichao, et al.
Pubblicazione: (2025)

Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from Scratch
di: Wen, Xueru, et al.
Pubblicazione: (2025)

Transferable Post-training via Inverse Value Learning
di: Lu, Xinyu, et al.
Pubblicazione: (2024)

Rule or Story, Which is a Better Commonsense Expression for Talking with Large Language Models?
di: Bian, Ning, et al.
Pubblicazione: (2024)

CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution
di: Xu, Ruiyang, et al.
Pubblicazione: (2024)

Towards Universal Dense Blocking for Entity Resolution
di: Wang, Tianshu, et al.
Pubblicazione: (2024)

REInstruct: Building Instruction Data from Unlabeled Corpus
di: Chen, Shu, et al.
Pubblicazione: (2024)

Executing Natural Language-Described Algorithms with Large Language Models: An Investigation
di: Zheng, Xin, et al.
Pubblicazione: (2024)

Meta-Cognitive Analysis: Evaluating Declarative and Procedural Knowledge in Datasets and Large Language Models
di: Li, Zhuoqun, et al.
Pubblicazione: (2024)

Open Grounded Planning: Challenges and Benchmark Construction
di: Guo, Shiguang, et al.
Pubblicazione: (2024)

MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning
di: Yuan, Qianhao, et al.
Pubblicazione: (2025)

On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation
di: Wen, Xueru, et al.
Pubblicazione: (2024)

URL: Universal Referential Knowledge Linking via Task-instructed Representation Compression
di: Li, Zhuoqun, et al.
Pubblicazione: (2024)

SAISA: Towards Multimodal Large Language Models with Both Training and Inference Efficiency
di: Yuan, Qianhao, et al.
Pubblicazione: (2025)

Tackling Length Inflation Without Trade-offs: Group Relative Reward Rescaling for Reinforcement Learning
di: Li, Zichao, et al.
Pubblicazione: (2026)

DOMAINEVAL: An Auto-Constructed Benchmark for Multi-Domain Code Generation
di: Zhu, Qiming, et al.
Pubblicazione: (2024)

Spiral of Silence: How is Large Language Model Killing Information Retrieval? -- A Case Study on Open Domain Question Answering
di: Chen, Xiaoyang, et al.
Pubblicazione: (2024)

StructEval: Deepen and Broaden Large Language Model Assessment via Structured Evaluation
di: Cao, Boxi, et al.
Pubblicazione: (2024)

All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG
di: Wang, Dan, et al.
Pubblicazione: (2026)

Few-shot Named Entity Recognition via Superposition Concept Discrimination
di: Chen, Jiawei, et al.
Pubblicazione: (2024)

Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
di: Yuan, Qianhao, et al.
Pubblicazione: (2026)

A Unified View of Delta Parameter Editing in Post-Trained Large-Scale Models
di: Tang, Qiaoyu, et al.
Pubblicazione: (2024)

Towards Scalable Automated Alignment of LLMs: A Survey
di: Cao, Boxi, et al.
Pubblicazione: (2024)

ChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Models
di: Bian, Ning, et al.
Pubblicazione: (2023)

SoFA: Shielded On-the-fly Alignment via Priority Rule Following
di: Lu, Xinyu, et al.
Pubblicazione: (2024)