knowledge editing
78 papers with code • 1 benchmarks • 3 datasets
Libraries
Use these libraries to find knowledge editing models and implementations
KnowEdit
WikiFactDiff
Most implemented papers
Cross-Lingual Knowledge Editing in Large Language Models
With the recent advancements in large language models (LLMs), knowledge editing has been shown as a promising technique to adapt LLMs to new knowledge without retraining from scratch.
Neuron-Level Knowledge Attribution in Large Language Models
zepingyu0512/neuron-attribution
•
•
Additionally, since most static methods typically only identify "value neurons" directly contributing to the final prediction, we propose a method for identifying "query neurons" which activate these "value neurons".
Retrieval-augmented Multilingual Knowledge Editing
vicky-wil/remake
•
•
Knowledge represented in Large Language Models (LLMs) is quite often incorrect and can also become obsolete over time.
Editing Language Model-based Knowledge Graph Embeddings
zjunlp/promptkg
•
•
To address this issue, we propose a new task of editing language model-based KG embeddings in this paper.
Can We Edit Factual Knowledge by In-Context Learning?
zce1112zslx/ike
•
•
Inspired by in-context learning (ICL), a new paradigm based on demonstration contexts without parameter updating, we explore whether ICL can edit factual knowledge.
MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions
The information stored in large language models (LLMs) falls out of date quickly, and retraining from scratch is often not an option.
EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models
zjunlp/easyedit
•
•
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cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect facts owing to outdated/noisy data.
Assessing Knowledge Editing in Language Models via Relation Perspective
weiyifan1023/knowledge-edit-based-on-relation-perspective
•
•
Knowledge Editing (KE) for modifying factual knowledge in Large Language Models (LLMs) has been receiving increasing attention.
A Comprehensive Study of Knowledge Editing for Large Language Models
zjunlp/easyedit
•
•
In this paper, we first define the knowledge editing problem and then provide a comprehensive review of cutting-edge approaches.
DeepEdit: Knowledge Editing as Decoding with Constraints
How to edit the knowledge in multi-step reasoning has become the major challenge in the knowledge editing (KE) of large language models (LLMs).
