Imagen de Portada

Reasons and Solutions for the Decline in Model Performance after Editing

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Huang, Xiusheng, Liu, Jiaxiang, Wang, Yequan, Liu, Kang
Formato:	Preprint
Publicado:	2024
Materias:	Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Commonsense Knowledge Editing Based on Free-Text in LLMs
por: Huang, Xiusheng, et al.
Publicado: (2024)

Capability Localization: Capabilities Can be Localized rather than Individual Knowledge
por: Huang, Xiusheng, et al.
Publicado: (2025)

If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs
por: Fan, Siqi, et al.
Publicado: (2025)

Mutual Enhancement Between Global Tokens and Patch Tokens: From Theory to Practice
por: Huang, Xiusheng, et al.
Publicado: (2026)

Multimodal Reasoning with Multimodal Knowledge Graph
por: Lee, Junlin, et al.
Publicado: (2024)

Enhancing Large Language Models with Pseudo- and Multisource- Knowledge Graphs for Open-ended Question Answering
por: Liu, Jiaxiang, et al.
Publicado: (2024)

Decoupling Reasoning and Knowledge Injection for In-Context Knowledge Editing
por: Wang, Changyue, et al.
Publicado: (2025)

Speculative Decoding: Performance or Illusion?
por: Liu, Xiaoxuan, et al.
Publicado: (2025)

Outdated Issue Aware Decoding for Reasoning Questions on Edited Knowledge
por: Sun, Zengkui, et al.
Publicado: (2024)

DocMEdit: Towards Document-Level Model Editing
por: Zeng, Li, et al.
Publicado: (2025)

FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models
por: Jiang, Kehan, et al.
Publicado: (2026)

ETCHR: Editing To Clarify and Harness Reasoning
por: Zhang, Beichen, et al.
Publicado: (2026)

SUCEA: Reasoning-Intensive Retrieval for Adversarial Fact-checking through Claim Decomposition and Editing
por: Liu, Hongjun, et al.
Publicado: (2025)

Socratic-PRMBench: Benchmarking Process Reward Models with Systematic Reasoning Patterns
por: Li, Xiang, et al.
Publicado: (2025)

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

Knowledge Updating? No More Model Editing! Just Selective Contextual Reasoning
por: He, Guoxiu, et al.
Publicado: (2025)

WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing
por: Hu, Chenhui, et al.
Publicado: (2024)

Pair-In, Pair-Out: Latent Multi-Token Prediction for Efficient LLMs
por: Tan, Wenhui, et al.
Publicado: (2026)

The Zero-Step Thinking: An Empirical Study of Mode Selection as Harder Early Exit in Reasoning Models
por: Tan, Yuqiao, et al.
Publicado: (2025)

Evaluating the Translation Performance of Large Language Models Based on Euas-20
por: Huang, Yan, et al.
Publicado: (2024)

Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent
por: Huang, Ziyang, et al.
Publicado: (2025)

Identifying Knowledge Editing Types in Large Language Models
por: Li, Xiaopeng, et al.
Publicado: (2024)

On the Superimposed Noise Accumulation Problem in Sequential Knowledge Editing of Large Language Models
por: Cao, Ding, et al.
Publicado: (2025)

MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models
por: Li, Jiachun, et al.
Publicado: (2024)

FAME: Towards Factual Multi-Task Model Editing
por: Zeng, Li, et al.
Publicado: (2024)

Evaluating Large Language Models for Financial Reasoning: A CFA-Based Benchmark Study
por: Yao, Xuan, et al.
Publicado: (2025)

Is Fine-Tuning an Effective Solution? Reassessing Knowledge Editing for Unstructured Data
por: Xiong, Hao, et al.
Publicado: (2025)

Multi-objective Large Language Model Alignment with Hierarchical Experts
por: Li, Zhuo, et al.
Publicado: (2025)

DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language Models
por: Zhu, Yakun, et al.
Publicado: (2025)

Large Language Model Bias Mitigation from the Perspective of Knowledge Editing
por: Chen, Ruizhe, et al.
Publicado: (2024)

Are Large Reasoning Models Good Translation Evaluators? Analysis and Performance Boost
por: Zhan, Runzhe, et al.
Publicado: (2025)

Stop Before You Fail: Operational Capability Boundaries for Mitigating Unproductive Reasoning in Large Reasoning Models
por: Zhang, Qingjie, et al.
Publicado: (2025)

Copy-as-Decode: Grammar-Constrained Parallel Prefill for LLM Editing
por: Liu, Ziyang
Publicado: (2026)

LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?
por: Wang, Jingyuan, et al.
Publicado: (2025)

ReasonAny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging
por: Yang, Junyao, et al.
Publicado: (2026)

LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language Models
por: Gui, Jiayi, et al.
Publicado: (2024)

Mitigating Context-Memory Conflicts in LLMs through Dynamic Cognitive Reconciliation Decoding
por: Zhou, Yigeng, et al.
Publicado: (2026)

Revisiting Model Interpolation for Efficient Reasoning
por: Wu, Taiqiang, et al.
Publicado: (2025)

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

Reasoning-Oriented and Analogy-Based Methods for Locating and Editing in Zero-Shot Event-Relational Reasoning
por: Tang, Jingyao, et al.
Publicado: (2025)