Moving the Eiffel Tower to ROME: Tracing and Editing Facts in GPT
We investigate the mechanisms underlying factual knowledge recall in auto-regressive transformer language models. To this end, we develop a method for identifying neuron activations that are capable of altering a model's factual predictions. Within GPT-2, this reveals two distinct sets of neurons that we hypothesize correspond to knowing an abstract fact and saying a concrete word, respectively. Based on this insight, we propose ROME, a simple and efficient rank-one model editing method for rewriting abstract facts in auto-regressive language models. For validation, we introduce CounterFact, a dataset of over twenty thousand rewritable facts, as well as tools to facilitate sensitive measurements of edit quality. Compared to previously-published knowledge editing methods, ROME achieves superior generalization and specificity.
Code (0)
등록된 구현이 없습니다.
Tasks
knowledge editingModel EditingSpecificityMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Image Hijacks: Adversarial Images can Control Generative Models at Runtime
Are foundation models secure against malicious actors? In this work, we focus on the image input to a vision-language model (VLM). We discover image hijacks, adversarial images that control the behaviour of VLMs at infer…
Language ModelingLanguage ModellingNon-Parametric Neural Style Transfer
It seems easy to imagine a photograph of the Eiffel Tower painted in the style of Vincent van Gogh's 'The Starry Night', but upon introspection it is difficult to precisely define what this would entail. What visual elem…
Style TransferTimeROME-DLM: Temporal Causal Tracing and Low-Rank Inference-Time Knowledge Editing for Masked Diffusion Language Models
Masked diffusion language models (MDLMs) such as LLaDA now rival autoregressive (AR) LLMs, but every existing knowledge-editing and unlearning method (ROME, MEMIT, etc.) targets AR transformers and either makes assumptio…
knowledge editingQuestion Answering Against Very-Large Text Collections
Question answering involves developing methods to extract useful information from large collections of documents. This is done with specialised search engines such as Answer Finder. The aim of Answer Finder is to provide…
Information RetrievalQuestion AnsweringRetrievalEditing as Unlearning: Are Knowledge Editing Methods Strong Baselines for Large Language Model Unlearning?
Large language Model (LLM) unlearning, i.e., selectively removing information from LLMs, is vital for responsible model deployment. Differently, LLM knowledge editing aims to modify LLM knowledge instead of removing it. …
In-Context Learningknowledge editingLanguage ModelingLanguage Modelling+1