Image de couverture de livre

From <Answer> to <Think>: Multidimensional Supervision of Reasoning Process for LLM Optimization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Beining, Su, Weihang, Tian, Hongtao, Yang, Tao, Zhou, Yujia, Yao, Ting, Ai, Qingyao, Liu, Yiqun
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Decoupling Reasoning and Knowledge Injection for In-Context Knowledge Editing
par: Wang, Changyue, et autres
Publié: (2025)

Joint Evaluation of Answer and Reasoning Consistency for Hallucination Detection in Large Reasoning Models
par: Wang, Changyue, et autres
Publié: (2025)

Improve Large Language Model Systems with User Logs
par: Wang, Changyue, et autres
Publié: (2026)

Enhancing Judgment Document Generation via Agentic Legal Information Collection and Rubric-Guided Optimization
par: Su, Weihang, et autres
Publié: (2026)

Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models
par: Su, Weihang, et autres
Publié: (2024)

ATACompressor: Adaptive Task-Aware Compression for Efficient Long-Context Processing in LLMs
par: Li, Xuancheng, et autres
Publié: (2026)

MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems
par: Ai, Qingyao, et autres
Publié: (2025)

RbFT: Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defects
par: Tu, Yiteng, et autres
Publié: (2025)

Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMs
par: Li, Xuancheng, et autres
Publié: (2026)

Analytical Search
par: Tu, Yiteng, et autres
Publié: (2026)

Chinese Court Simulation with LLM-Based Agent System
par: Zhang, Kaiyuan, et autres
Publié: (2025)

MulFeRL: Enhancing Reinforcement Learning with Verbal Feedback in a Multi-turn Loop
par: Li, Xuancheng, et autres
Publié: (2026)

Beyond Exposure: Optimizing Ranking Fairness with Non-linear Time-Income Functions
par: Li, Xuancheng, et autres
Publié: (2026)

How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study
par: Zhu, Shuqi, et autres
Publié: (2026)

Multi-Field Tool Retrieval
par: Tang, Yichen, et autres
Publié: (2026)

Decoupling Knowledge and Task Subspaces for Composable Parametric Retrieval Augmented Generation
par: Su, Weihang, et autres
Publié: (2026)

Equity vs. Equality: Optimizing Ranking Fairness for Tailored Provider Needs
par: Tu, Yiteng, et autres
Publié: (2026)

Wikiformer: Pre-training with Structured Information of Wikipedia for Ad-hoc Retrieval
par: Su, Weihang, et autres
Publié: (2023)

Gender Biased Legal Case Retrieval System on Users' Decision Process
par: Zhang, Ruizhe, et autres
Publié: (2024)

Generalized Pseudo-Relevance Feedback
par: Tu, Yiteng, et autres
Publié: (2025)

Augmenting Multi-Agent Communication with State Delta Trajectory
par: Tang, Yichen, et autres
Publié: (2025)

Investigating Prosocial Behavior Theory in LLM Agents under Policy-Induced Inequities
par: Zhou, Yujia, et autres
Publié: (2025)

Reinforcement Learning to Rank Using Coarse-grained Rewards
par: Tu, Yiteng, et autres
Publié: (2022)

SurGE: A Benchmark and Evaluation Framework for Scientific Survey Generation
par: Su, Weihang, et autres
Publié: (2025)

Knowledge Editing through Chain-of-Thought
par: Wang, Changyue, et autres
Publié: (2024)

DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models
par: Su, Weihang, et autres
Publié: (2024)

Dynamic and Parametric Retrieval-Augmented Generation
par: Su, Weihang, et autres
Publié: (2025)

Option-ID Based Elimination For Multiple Choice Questions
par: Zhu, Zhenhao, et autres
Publié: (2025)

LeKUBE: A Legal Knowledge Update BEnchmark
par: Wang, Changyue, et autres
Publié: (2024)

CrossPT-EEG: A Benchmark for Cross-Participant and Cross-Time Generalization of EEG-based Visual Decoding
par: Zhu, Shuqi, et autres
Publié: (2024)

JuDGE: Benchmarking Judgment Document Generation for Chinese Legal System
par: Su, Weihang, et autres
Publié: (2025)

From Faithfulness to Correctness: Generative Reward Models that Think Critically
par: Ma, Qiyao, et autres
Publié: (2025)

CAPO: Towards Enhancing LLM Reasoning through Generative Credit Assignment
par: Xie, Guofu, et autres
Publié: (2025)

Beyond Scalar Reward Model: Learning Generative Judge from Preference Data
par: Ye, Ziyi, et autres
Publié: (2024)

Mitigating Entity-Level Hallucination in Large Language Models
par: Su, Weihang, et autres
Publié: (2024)

Parametric Social Identity Injection and Diversification in Public Opinion Simulation
par: Wang, Hexi, et autres
Publié: (2026)

Parametric Retrieval Augmented Generation
par: Su, Weihang, et autres
Publié: (2025)

What Scales in Cross-Entropy Scaling Law?
par: Yan, Junxi, et autres
Publié: (2025)

TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation
par: Du, Bangde, et autres
Publié: (2025)

LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods
par: Li, Haitao, et autres
Publié: (2024)