paper-with-me

홈 › Papers

Mass-Editing Memory in a Transformer

2022-10-13 · Kevin Meng, Arnab Sen Sharma, Alex Andonian, Yonatan Belinkov, David Bau

Recent work has shown exciting promise in updating large language models with new memories, so as to replace obsolete information or add specialized knowledge. However, this line of work is predominantly limited to updating single associations. We develop MEMIT, a method for directly updating a language model with many memories, demonstrating experimentally that it can scale up to thousands of associations for GPT-J (6B) and GPT-NeoX (20B), exceeding prior work by orders of magnitude. Our code and data are at https://memit.baulab.info.

📄 PDF Abstract BibTeX arXiv:2210.07229

Code (2)

kmeng01/memit 공식 구현 pytorch
orange-opensource/wikifactdiff pytorch

Tasks

Language ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

GPT-NeoX GPT-NeoX is an autoregressive transformer decoder model whose architecture largely follows that of GPT-3, with a few notable deviations. The model has 20 billion parameters…

Similar Papers 제목 키워드 기반

NAMET: Robust Massive Model Editing via Noise-Aware Memory Optimization

2025-05-17 · Yanbo Dai, Zhenlan Ji, Zongjie Li, Shuai Wang

Model editing techniques are essential for efficiently updating knowledge in large language models (LLMs). However, the effectiveness of existing approaches degrades in massive editing scenarios, particularly when evalua…

AttributeModel Editing

Mass-Editing Memory with Attention in Transformers: A cross-lingual exploration of knowledge

2025-02-04 · Daniel Tamayo, Aitor Gonzalez-Agirre, Javier Hernando, Marta Villegas

Recent research has explored methods for updating and modifying factual knowledge in large language models, often focusing on specific multi-layer perceptron blocks. This study expands on this work by examining the effec…

knowledge editing

A Unified Framework for Model Editing

2024-03-21 · Akshat Gupta, Dev Sajnani, Gopala Anumanchipalli

ROME and MEMIT are largely believed to be two different model editing algorithms, with the major difference between them being the ability to perform batched edits. In this paper, we unify these two algorithms under a si…

MemorizationmodelModel Editing

Editing Massive Concepts in Text-to-Image Diffusion Models

2024-03-20 · Tianwei Xiong, Enze Xie, Yue Wu, Zhenguo Li 외

Text-to-image diffusion models suffer from the risk of generating outdated, copyrighted, incorrect, and biased content. While previous methods have mitigated the issues on a small scale, it is essential to handle them si…

Model Editing

Massive Editing for Large Language Models via Meta Learning

2023-11-08 · Chenmien Tan, Ge Zhang, Jie Fu

While large language models (LLMs) have enabled learning knowledge from the pre-training corpora, the acquired knowledge may be fundamentally incorrect or outdated over time, which necessitates rectifying the knowledge o…

Fact CheckingLanguage ModelingLanguage ModellingMeta-Learning+2