paper-with-me

Papers

EVEDIT: Event-based Knowledge Editing with Deductive Editing Boundaries

2024-02-17 · Jiateng Liu, Pengfei Yu, Yuji Zhang, Sha Li, Zixuan Zhang, Heng Ji

The dynamic nature of real-world information necessitates efficient knowledge editing (KE) in large language models (LLMs) for knowledge updating. However, current KE approaches, which typically operate on (subject, relation, object) triples, ignore the contextual information and the relation among different knowledge. Such editing methods could thus encounter an uncertain editing boundary, leaving a lot of relevant knowledge in ambiguity: Queries that could be answered pre-edit cannot be reliably answered afterward. In this work, we analyze this issue by introducing a theoretical framework for KE that highlights an overlooked set of knowledge that remains unchanged and aids in knowledge deduction during editing, which we name as the deduction anchor. We further address this issue by proposing a novel task of event-based knowledge editing that pairs facts with event descriptions. This task manifests not only a closer simulation of real-world editing scenarios but also a more logically sound setting, implicitly defining the deduction anchor to address the issue of indeterminate editing boundaries. We empirically demonstrate the superiority of event-based editing over the existing setting on resolving uncertainty in edited models, and curate a new benchmark dataset EvEdit derived from the CounterFact dataset. Moreover, while we observe that the event-based setting is significantly challenging for existing approaches, we propose a novel approach Self-Edit that showcases stronger performance, achieving 55.6% consistency improvement while maintaining the naturalness of generation.

📄 PDF Abstract BibTeX arXiv:2402.11324

Code (0)

등록된 구현이 없습니다.

Tasks

knowledge editing

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Event-level Knowledge Editing

2024-02-20 · Hao Peng, Xiaozhi Wang, Chunyang Li, Kaisheng Zeng 외

Knowledge editing aims at updating knowledge of large language models (LLMs) to prevent them from becoming outdated. Existing work edits LLMs at the level of factual knowledge triplets. However, natural knowledge updates…

knowledge editingTriplet

EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models

2023-08-14 · Peng Wang, Ningyu Zhang, Bozhong Tian, Zekun Xi 외

Large Language Models (LLMs) usually suffer from knowledge cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect facts owing to outdated/noisy data. To this end, many kno…

knowledge editing

SCAN: Sparse Circuit Anchor Interpretable Neuron for Lifelong Knowledge Editing

2026-03-16 · Yuhuan Liu, Haitian Zhong, Xinyuan Xia, Qiang Liu 외 arxiv

Large Language Models (LLMs) often suffer from catastrophic forgetting and collapse during sequential knowledge editing. This vulnerability stems from the prevailing dense editing paradigm, which treats models as black b…

knowledge editing

MEMLA: Enhancing Multilingual Knowledge Editing with Neuron-Masked Low-Rank Adaptation

2024-06-17 · Jiakuan Xie, Pengfei Cao, YuHeng Chen, Yubo Chen 외

Knowledge editing aims to adjust the knowledge within large language models (LLMs) to prevent their responses from becoming obsolete or inaccurate. However, existing works on knowledge editing are primarily conducted in …

knowledge editing

DeltaEdit: Enhancing Sequential Editing in Large Language Models by Controlling Superimposed Noise

2025-05-12 · Ding Cao, Yuchen Cai, Rongxi Guo, Xuesong He 외

Sequential knowledge editing techniques aim to continuously update the knowledge in large language models at a low cost, preventing the models from generating outdated or incorrect information. However, existing sequenti…

knowledge editing