Imagen de Portada

Disentangling Knowledge Representations for Large Language Model Editing

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Mengqi, Zhou, Zisheng, Ye, Xiaotian, Liu, Qiang, Ren, Zhaochun, Chen, Zhumin, Ren, Pengjie
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Knowledge Graph Enhanced Large Language Model Editing
por: Zhang, Mengqi, et al.
Publicado: (2024)

Uncovering Overfitting in Large Language Model Editing
por: Zhang, Mengqi, et al.
Publicado: (2024)

Uncovering Context Reliance in Unstructured Knowledge Editing
por: Zhou, Zisheng, et al.
Publicado: (2026)

UIPE: Enhancing LLM Unlearning by Removing Knowledge Related to Forgetting Targets
por: Wang, Wenyu, et al.
Publicado: (2025)

Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse
por: Zhang, Chi, et al.
Publicado: (2026)

Enhancing Multi-hop Reasoning through Knowledge Erasure in Large Language Model Editing
por: Zhang, Mengqi, et al.
Publicado: (2024)

Self-Supervised Position Debiasing for Large Language Models
por: Liu, Zhongkun, et al.
Publicado: (2024)

ASLoRA: Adaptive Sharing Low-Rank Adaptation Across Layers
por: Hu, Junyan, et al.
Publicado: (2024)

Evolution without Large Models: Training Language Model with Task Principles
por: Zhu, Minghang, et al.
Publicado: (2025)

KnowTuning: Knowledge-aware Fine-tuning for Large Language Models
por: Lyu, Yougang, et al.
Publicado: (2024)

Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents
por: Sun, Weiwei, et al.
Publicado: (2023)

Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answering
por: Shi, Zhengliang, et al.
Publicado: (2024)

MELoRA: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-Tuning
por: Ren, Pengjie, et al.
Publicado: (2024)

Self-Adaptive Cognitive Debiasing for Large Language Models in Decision-Making
por: Lyu, Yougang, et al.
Publicado: (2025)

MEFT: Memory-Efficient Fine-Tuning through Sparse Adapter
por: Hao, Jitai, et al.
Publicado: (2024)

Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systems
por: Zhu, Minghang, et al.
Publicado: (2025)

Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models
por: Shi, Zhengliang, et al.
Publicado: (2025)

MADS: Model-Aware Diverse Core Set Selection for Instruction Tuning
por: Bai, Yi, et al.
Publicado: (2026)

Uncovering Entity Identity Confusion in Multimodal Knowledge Editing
por: Wu, Shu, et al.
Publicado: (2026)

Open Problems and a Hypothetical Path Forward in LLM Knowledge Paradigms
por: Ye, Xiaotian, et al.
Publicado: (2025)

How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study
por: Ju, Tianjie, et al.
Publicado: (2024)

Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agents
por: Shi, Zhengliang, et al.
Publicado: (2024)

A Multi-Agent Conversational Recommender System
por: Fang, Jiabao, et al.
Publicado: (2024)

Cognitive Biases in Large Language Models for News Recommendation
por: Lyu, Yougang, et al.
Publicado: (2024)

A Cooperative Multi-Agent Framework for Zero-Shot Named Entity Recognition
por: Wang, Zihan, et al.
Publicado: (2025)

Towards Localized and Disentangled Knowledge Editing for Multimodal Large Language Models
por: Gu, Leijiang, et al.
Publicado: (2026)

On the Hidden Costs of Counterfactual Knowledge Training in LLM Unlearning
por: Ye, Xiaotian, et al.
Publicado: (2026)

Joint Flashback Adaptation for Forgetting-Resistant Instruction Tuning
por: Zhao, Yukun, et al.
Publicado: (2025)

MUSE: Integrating Multi-Knowledge for Knowledge Graph Completion
por: Liu, Pengjie
Publicado: (2024)

OpenReward: Learning to Reward Long-form Agentic Tasks via Reinforcement Learning
por: Hu, Ziyou, et al.
Publicado: (2025)

MUSE: Multi-Knowledge Passing on the Edges, Boosting Knowledge Graph Completion
por: Liu, Pengjie
Publicado: (2024)

Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers
por: Shi, Zhengliang, et al.
Publicado: (2025)

A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone
por: Hao, Jitai, et al.
Publicado: (2025)

Neighboring Perturbations of Knowledge Editing on Large Language Models
por: Ma, Jun-Yu, et al.
Publicado: (2024)

Inspecting and Editing Knowledge Representations in Language Models
por: Hernandez, Evan, et al.
Publicado: (2023)

MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization
por: Lyu, Yougang, et al.
Publicado: (2024)

Disentangling Reasoning and Knowledge in Medical Large Language Models
por: Thapa, Rahul, et al.
Publicado: (2025)

Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models
por: Hu, Chenhui, et al.
Publicado: (2024)

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

Exploring Information Processing in Large Language Models: Insights from Information Bottleneck Theory
por: Yang, Zhou, et al.
Publicado: (2025)