Copertina

Unveiling the Pitfalls of Knowledge Editing for Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Zhoubo, Zhang, Ningyu, Yao, Yunzhi, Wang, Mengru, Chen, Xi, Chen, Huajun
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Databases Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Detoxifying Large Language Models via Knowledge Editing
di: Wang, Mengru, et al.
Pubblicazione: (2024)

Knowledge Circuits in Pretrained Transformers
di: Yao, Yunzhi, et al.
Pubblicazione: (2024)

EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models
di: Wang, Peng, et al.
Pubblicazione: (2023)

WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models
di: Wang, Peng, et al.
Pubblicazione: (2024)

EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models
di: Xu, Ziwen, et al.
Pubblicazione: (2025)

Exploring Model Kinship for Merging Large Language Models
di: Hu, Yedi, et al.
Pubblicazione: (2024)

To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models
di: Tian, Bozhong, et al.
Pubblicazione: (2024)

Editing Conceptual Knowledge for Large Language Models
di: Wang, Xiaohan, et al.
Pubblicazione: (2024)

CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners
di: Yao, Yunzhi, et al.
Pubblicazione: (2025)

Aligning Agentic World Models via Knowledgeable Experience Learning
di: Ren, Baochang, et al.
Pubblicazione: (2026)

A Comprehensive Study of Knowledge Editing for Large Language Models
di: Zhang, Ningyu, et al.
Pubblicazione: (2024)

Knowledge Mechanisms in Large Language Models: A Survey and Perspective
di: Wang, Mengru, et al.
Pubblicazione: (2024)

InstructEdit: Instruction-based Knowledge Editing for Large Language Models
di: Zhang, Ningyu, et al.
Pubblicazione: (2024)

Can We Edit Multimodal Large Language Models?
di: Cheng, Siyuan, et al.
Pubblicazione: (2023)

ADS-Edit: A Multimodal Knowledge Editing Dataset for Autonomous Driving Systems
di: Wang, Chenxi, et al.
Pubblicazione: (2025)

How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training
di: Ou, Yixin, et al.
Pubblicazione: (2025)

Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics
di: Xu, Ziwen, et al.
Pubblicazione: (2026)

ReLearn: Unlearning via Learning for Large Language Models
di: Xu, Haoming, et al.
Pubblicazione: (2025)

Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms
di: Wang, Mengru, et al.
Pubblicazione: (2025)

LightMem: Lightweight and Efficient Memory-Augmented Generation
di: Fang, Jizhan, et al.
Pubblicazione: (2025)

KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality
di: Ren, Baochang, et al.
Pubblicazione: (2025)

OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System
di: Zhang, Ningyu, et al.
Pubblicazione: (2024)

LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities
di: Zhu, Yuqi, et al.
Pubblicazione: (2023)

Spatial Knowledge Graph-Guided Multimodal Synthesis
di: Xue, Yida, et al.
Pubblicazione: (2025)

OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation Models
di: Xue, Yida, et al.
Pubblicazione: (2026)

Agent Planning with World Knowledge Model
di: Qiao, Shuofei, et al.
Pubblicazione: (2024)

Reducing Hallucination in Vision-Language Models via Stage-wise Preference Optimization under Distribution Shift
di: Xu, Qinwu
Pubblicazione: (2026)

OceanGym: A Benchmark Environment for Underwater Embodied Agents
di: Xue, Yida, et al.
Pubblicazione: (2025)

MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
di: Wang, Chenxi, et al.
Pubblicazione: (2024)

SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement
di: Fang, Runnan, et al.
Pubblicazione: (2025)

Agentic Knowledgeable Self-awareness
di: Qiao, Shuofei, et al.
Pubblicazione: (2025)

Unveiling Uncertainty: A Deep Dive into Calibration and Performance of Multimodal Large Language Models
di: Chen, Zijun, et al.
Pubblicazione: (2024)

VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark
di: Huang, Han, et al.
Pubblicazione: (2024)

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
di: Wang, Mengru, et al.
Pubblicazione: (2025)

Continual Multimodal Knowledge Graph Construction
di: Chen, Xiang, et al.
Pubblicazione: (2023)

ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging
di: Xu, Haoming, et al.
Pubblicazione: (2025)

Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge
di: Lin, Yuanze, et al.
Pubblicazione: (2024)

OODBench: Out-of-Distribution Benchmark for Large Vision-Language Models
di: Lin, Ling, et al.
Pubblicazione: (2026)

Improving Image Captioning Descriptiveness by Ranking and LLM-based Fusion
di: Celona, Luigi, et al.
Pubblicazione: (2023)

ChemVA: Advancing Large Language Models on Chemical Reaction Diagrams Understanding
di: Rao, Mingyang, et al.
Pubblicazione: (2026)