Image de couverture de livre

Towards Stepwise Domain Knowledge-Driven Reasoning Optimization and Reflection Improvement

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Chengyuan, Wang, Shihang, Qing, Lizhi, Song, Kaisong, Cao, Junjie, Lin, Jun, Zhang, Ji, Li, Ang, Kuang, Kun, Wu, Fei
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Learning to Solve Domain-Specific Calculation Problems with Knowledge-Intensive Programs Generator
par: Liu, Chengyuan, et autres
Publié: (2024)

Gold Panning in Vocabulary: An Adaptive Method for Vocabulary Expansion of Domain-Specific LLMs
par: Liu, Chengyuan, et autres
Publié: (2024)

More Than Catastrophic Forgetting: Integrating General Capabilities For Domain-Specific LLMs
par: Liu, Chengyuan, et autres
Publié: (2024)

LeCoDe: A Benchmark Dataset for Interactive Legal Consultation Dialogue Evaluation
par: Yuan, Weikang, et autres
Publié: (2025)

From Graph to Word Bag: Introducing Domain Knowledge to Confusing Charge Prediction
par: Li, Ang, et autres
Publié: (2024)

RexUniNLU: Recursive Method with Explicit Schema Instructor for Universal NLU
par: Liu, Chengyuan, et autres
Publié: (2024)

Enhancing Court View Generation with Knowledge Injection and Guidance
par: Li, Ang, et autres
Publié: (2024)

Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning
par: Wang, Xiyao, et autres
Publié: (2024)

Do Vision-Language Models Truly Perform Vision Reasoning? A Rigorous Study of the Modality Gap
par: Xu, Yige, et autres
Publié: (2026)

Evolving Knowledge Distillation with Large Language Models and Active Learning
par: Liu, Chengyuan, et autres
Publié: (2024)

P2S: Probabilistic Process Supervision for General-Domain Reasoning Question Answering
par: Zhong, Wenlin, et autres
Publié: (2026)

Towards Adaptive Open-Set Object Detection via Category-Level Collaboration Knowledge Mining
par: Ji, Yuqi, et autres
Publié: (2026)

Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent Collaboration
par: Yuan, Weikang, et autres
Publié: (2024)

Bridging Stepwise Lab-Informed Pretraining and Knowledge-Guided Learning for Diagnostic Reasoning
par: Hu, Pengfei, et autres
Publié: (2024)

SGR: A Stepwise Reasoning Framework for LLMs with External Subgraph Generation
par: Zhang, Xin, et autres
Publié: (2026)

STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning
par: Zhang, Junjie, et autres
Publié: (2026)

Rewrite to Jailbreak: Discover Learnable and Transferable Implicit Harmfulness Instruction
par: Huang, Yuting, et autres
Publié: (2025)

AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation
par: Tang, Zihao, et autres
Publié: (2024)

When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs
par: Wang, Yongjie, et autres
Publié: (2025)

LangGFM: A Large Language Model Alone Can be a Powerful Graph Foundation Model
par: Lin, Tianqianjin, et autres
Publié: (2024)

Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO
par: Chen, Peter, et autres
Publié: (2025)

Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback
par: Lin, Yen-Ting, et autres
Publié: (2025)

A Stepwise-Enhanced Reasoning Framework for Large Language Models Based on External Subgraph Generation
par: Zhang, Xin, et autres
Publié: (2025)

StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason
par: Zhang, Kaiyi, et autres
Publié: (2025)

DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning
par: Wu, Yuanhao, et autres
Publié: (2025)

Constrained Language Model Policy Optimization via Risk-aware Stepwise Alignment
par: Zhang, Lijun, et autres
Publié: (2025)

Embracing Imperfection: Simulating Students with Diverse Cognitive Levels Using LLM-based Agents
par: Wu, Tao, et autres
Publié: (2025)

StreamBench: Towards Benchmarking Continuous Improvement of Language Agents
par: Wu, Cheng-Kuang, et autres
Publié: (2024)

Promoting Efficient Reasoning with Verifiable Stepwise Reward
par: Yue, Chuhuai, et autres
Publié: (2025)

WisdomInterrogatory (LuWen): An Open-Source Legal Large Language Model Technical Report
par: Wu, Yiquan, et autres
Publié: (2026)

Enhancing Mathematical Reasoning in LLMs by Stepwise Correction
par: Wu, Zhenyu, et autres
Publié: (2024)

Search-based Software Testing Driven by Domain Knowledge: Reflections and New Perspectives
par: Formica, Federico, et autres
Publié: (2025)

CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning
par: Nasvytis, Linas, et autres
Publié: (2026)

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization
par: Jin, Zhensheng, et autres
Publié: (2025)

STRIDE-ED: A Strategy-Grounded Stepwise Reasoning Framework for Empathetic Dialogue Systems
par: Ji, Hongru, et autres
Publié: (2026)

Adversarial Attack-Defense Co-Evolution for LLM Safety Alignment via Tree-Group Dual-Aware Search and Optimization
par: Li, Xurui, et autres
Publié: (2025)

Causal-Driven Feature Evaluation for Cross-Domain Image Classification
par: Cheng, Chen, et autres
Publié: (2026)

Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing
par: Wang, Wenguan, et autres
Publié: (2022)

Towards Adaptive ML Benchmarks: Web-Agent-Driven Construction, Domain Expansion, and Metric Optimization
par: Jia, Hangyi, et autres
Publié: (2025)

Optimize Incompatible Parameters through Compatibility-aware Knowledge Integration
par: Lv, Zheqi, et autres
Publié: (2025)