Imagen de Portada

Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lei, Zhenyu, Wu, Qiong, Dong, Jianxiong, He, Yinhan, Dodwell, Emily, Dong, Yushun, Li, Jundong
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

MolEdit: Knowledge Editing for Multimodal Molecule Language Models
por: Lei, Zhenyu, et al.
Publicado: (2025)

Learning from Diverse Reasoning Paths with Routing and Collaboration
por: Lei, Zhenyu, et al.
Publicado: (2025)

Harnessing Large Language Models for Disaster Management: A Survey
por: Lei, Zhenyu, et al.
Publicado: (2025)

Mechanistic Circuit-Based Knowledge Editing in Large Language Models
por: Zhao, Tianyi, et al.
Publicado: (2026)

Explaining Graph Neural Networks with Large Language Models: A Counterfactual Perspective for Molecular Property Prediction
por: He, Yinhan, et al.
Publicado: (2024)

Knowledge Graph-Enhanced Large Language Models via Path Selection
por: Liu, Haochen, et al.
Publicado: (2024)

IAPO: Information-Aware Policy Optimization for Token-Efficient Reasoning
por: He, Yinhan, et al.
Publicado: (2026)

Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective
por: Dong, Yushun, et al.
Publicado: (2024)

SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens
por: He, Yinhan, et al.
Publicado: (2025)

KG-CF: Knowledge Graph Completion with Context Filtering under the Guidance of Large Language Models
por: Zheng, Zaiyi, et al.
Publicado: (2025)

CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models
por: Wang, Song, et al.
Publicado: (2024)

SOMA: Efficient Multi-turn LLM Serving via Small Language Model
por: Cheng, Xueqi, et al.
Publicado: (2026)

ST-FiT: Inductive Spatial-Temporal Forecasting with Limited Training Data
por: Lei, Zhenyu, et al.
Publicado: (2024)

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs
por: Zhao, Tianyi, et al.
Publicado: (2026)

LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer?
por: Cheng, Xueqi, et al.
Publicado: (2026)

InComeS: Integrating Compression and Selection Mechanisms into LLMs for Efficient Model Editing
por: Li, Shuaiyi, et al.
Publicado: (2025)

Saliency-Aware Multi-Route Thinking: Revisiting Vision-Language Reasoning
por: Shi, Mingjia, et al.
Publicado: (2026)

CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs
por: Li, Li, et al.
Publicado: (2025)

Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models
por: Wu, Wenshan, et al.
Publicado: (2024)

Resolving Editing-Unlearning Conflicts: A Knowledge Codebook Framework for Large Language Model Updating
por: Zhang, Binchi, et al.
Publicado: (2025)

Few-Shot Graph Out-of-Distribution Detection with LLMs
por: Xu, Haoyan, et al.
Publicado: (2025)

Enhancing Mathematical Reasoning in LLMs by Stepwise Correction
por: Wu, Zhenyu, et al.
Publicado: (2024)

MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs
por: Wang, Lei, et al.
Publicado: (2024)

Balancing Knowledge Updates: Toward Unified Modular Editing in LLMs
por: Liu, Jiahao, et al.
Publicado: (2025)

IDEA: A Flexible Framework of Certified Unlearning for Graph Neural Networks
por: Dong, Yushun, et al.
Publicado: (2024)

Mission Impossible: Feedback-Guided Dynamic Interactive Planning for Improving Reasoning on LLMs
por: Yan, Dong, et al.
Publicado: (2025)

On the Robustness of Knowledge Editing for Detoxification
por: Dong, Ming, et al.
Publicado: (2026)

A Benchmark for Fairness-Aware Graph Learning
por: Dong, Yushun, et al.
Publicado: (2024)

Energy-Based Models for Predicting Mutational Effects on Proteins
por: Soga, Patrick, et al.
Publicado: (2025)

Knowledge Editing for Large Language Models: A Survey
por: Wang, Song, et al.
Publicado: (2023)

ReAD: Reinforcement-Guided Capability Distillation for Large Language Models
por: Cheng, Xueqi, et al.
Publicado: (2026)

Vocab Diet: Reshaping the Vocabulary of LLMs via Vector Arithmetic
por: Reif, Yuval, et al.
Publicado: (2025)

MEMIT-Merge: Addressing MEMIT's Key-Value Conflicts in Same-Subject Batch Editing for LLMs
por: Dong, Zilu, et al.
Publicado: (2025)

Benchmarking LLMs' Mathematical Reasoning with Unseen Random Variables Questions
por: Hong, Zijin, et al.
Publicado: (2025)

Breaking Thought Patterns: A Multi-Dimensional Reasoning Framework for LLMs
por: Tang, Xintong, et al.
Publicado: (2025)

Few-shot Knowledge Graph Relational Reasoning via Subgraph Adaptation
por: Liu, Haochen, et al.
Publicado: (2024)

Reward Reasoning Model
por: Guo, Jiaxin, et al.
Publicado: (2025)

ProtoReasoning: Prototypes as the Foundation for Generalizable Reasoning in LLMs
por: He, Feng, et al.
Publicado: (2025)

PAVE: Premise-Aware Validation and Editing for Retrieval-Augmented LLMs
por: Huang, Tianyi, et al.
Publicado: (2026)

InstructERC: Reforming Emotion Recognition in Conversation with Multi-task Retrieval-Augmented Large Language Models
por: Lei, Shanglin, et al.
Publicado: (2023)