Imagen de Portada

Micro-Act: Mitigating Knowledge Conflict in LLM-based RAG via Actionable Self-Reasoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Huo, Nan, Li, Jinyang, Qin, Bowen, Qu, Ge, Li, Xiaolong, Li, Xiaodong, Ma, Chenhao, Cheng, Reynold
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQL
por: Qu, Ge, et al.
Publicado: (2025)

Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generation
por: Qu, Ge, et al.
Publicado: (2024)

Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agents
por: Li, Jinyang, et al.
Publicado: (2024)

SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications
por: Li, Jinyang, et al.
Publicado: (2025)

ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM
por: Su, Zhaochen, et al.
Publicado: (2024)

BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactions
por: Huo, Nan, et al.
Publicado: (2025)

Revisiting Task-Oriented Dataset Search in the Era of Large Language Models: Challenges, Benchmark, and Solution
por: Wei, Zixin, et al.
Publicado: (2025)

A Survey on Knowledge Distillation of Large Language Models
por: Xu, Xiaohan, et al.
Publicado: (2024)

Self-playing Adversarial Language Game Enhances LLM Reasoning
por: Cheng, Pengyu, et al.
Publicado: (2024)

Toward Robust GraphRAG: Mitigating Retrieval Drift and Hallucination from Imperfect Knowledge Graphs
por: Ma, Yizhuo, et al.
Publicado: (2026)

UR$^2$: Unify RAG and Reasoning through Reinforcement Learning
por: Li, Weitao, et al.
Publicado: (2025)

RbtAct: Rebuttal as Supervision for Actionable Review Feedback Generation
por: Wu, Sihong, et al.
Publicado: (2026)

Finding Locally Densest Subgraphs: Convex Programming with Edge and Triangle Density
por: Yang, Yi, et al.
Publicado: (2025)

Diagnosing Knowledge Conflict in Multimodal Long-Chain Reasoning
por: Tang, Jing, et al.
Publicado: (2026)

SAGE: A Framework of Precise Retrieval for RAG
por: Zhang, Jintao, et al.
Publicado: (2025)

Brainstorming Brings Power to Large Language Models of Knowledge Reasoning
por: Qin, Zining, et al.
Publicado: (2024)

Nitrogen/Oxygen Co‐Doped Carbon Quantum Dots with Efficient High Color‐Purity Red Emission for Bright Electroluminescent LEDs
por: Chenhao Li, et al.
Publicado: (2025)

Nitrogen/Oxygen Co‐Doped Carbon Quantum Dots with Efficient High Color‐Purity Red Emission for Bright Electroluminescent LEDs
por: Chenhao Li, et al.
Publicado: (2025)

ConflictRAG: Detecting and Resolving Knowledge Conflicts in Retrieval Augmented Generation
por: Wang, Chenyu, et al.
Publicado: (2026)

Selective Temporal Knowledge Graph Reasoning
por: Hou, Zhongni, et al.
Publicado: (2024)

Understanding Users' Privacy Perceptions Towards LLM's RAG-based Memory
por: Zhang, Shuning, et al.
Publicado: (2025)

Mitigating Knowledge Conflicts in Language Model-Driven Question Answering
por: Cao, Han, et al.
Publicado: (2024)

Driving-RAG: Driving Scenarios Embedding, Search, and RAG Applications
por: Chang, Cheng, et al.
Publicado: (2025)

Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG
por: Du, Xueying, et al.
Publicado: (2024)

Exploring Knowledge Conflicts for Faithful LLM Reasoning: Benchmark and Method
por: Zhao, Tianzhe, et al.
Publicado: (2026)

Bayesian Brain Edge-Based Connectivity (BBeC): a Bayesian model for brain edge-based connectivity inference
por: Li, Zijing, et al.
Publicado: (2025)

Knowledge Graph Reasoning with Self-supervised Reinforcement Learning
por: Ma, Ying, et al.
Publicado: (2024)

From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG
por: Wu, Wenhao, et al.
Publicado: (2026)

Towards Transparent RAG: Fostering Evidence Traceability in LLM Generation via Reinforcement Learning
por: Ren, Jingyi, et al.
Publicado: (2025)

OAK -- Onboarding with Actionable Knowledge
por: Devènes, Steve, et al.
Publicado: (2025)

Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards
por: Tamber, Manveer Singh, et al.
Publicado: (2025)

T-GRAG: A Dynamic GraphRAG Framework for Resolving Temporal Conflicts and Redundancy in Knowledge Retrieval
por: Li, Dong, et al.
Publicado: (2025)

The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation
por: Cheng, Shuaizhi, et al.
Publicado: (2026)

Count Counts: Motivating Exploration in LLM Reasoning with Count-based Intrinsic Rewards
por: Zhang, Xuan, et al.
Publicado: (2025)

Assessing and Mitigating Medical Knowledge Drift and Conflicts in Large Language Models
por: Wu, Weiyi, et al.
Publicado: (2025)

SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning
por: Chen, Jiaqi, et al.
Publicado: (2025)

Mixture Policy based Multi-Hop Reasoning over N-tuple Temporal Knowledge Graphs
por: Hou, Zhongni, et al.
Publicado: (2025)

RAGXplain: From Explainable Evaluation to Actionable Guidance of RAG Pipelines
por: Cohen, Dvir, et al.
Publicado: (2025)

Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models
por: Jin, Zhuoran, et al.
Publicado: (2024)

Pre-trained Model-based Actionable Warning Identification: A Feasibility Study
por: Ge, Xiuting, et al.
Publicado: (2024)