paper-with-me

홈 › Papers

Moving the Eiffel Tower to ROME: Tracing and Editing Facts in GPT

2021-11-16 · ACL ARR November 2021 11 · Anonymous

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

knowledge editingModel EditingSpecificity

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Image Hijacks: Adversarial Images can Control Generative Models at Runtime

2023-09-01 · Luke Bailey, Euan Ong, Stuart Russell, Scott Emmons

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 Modelling

Non-Parametric Neural Style Transfer

2021-08-29 · Nicholas Kolkin

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 Transfer

TimeROME-DLM: Temporal Causal Tracing and Low-Rank Inference-Time Knowledge Editing for Masked Diffusion Language Models

2026-06-11 · Zhengtao Yao, Liuyang Song, Hongbo Zhang, Chenhao Wei 외 arxiv

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 editing

Question Answering Against Very-Large Text Collections

2013-04-26 · Leon Derczynski, Richard Shaw, Ben Solway, Jun Wang

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 AnsweringRetrieval

Editing as Unlearning: Are Knowledge Editing Methods Strong Baselines for Large Language Model Unlearning?

2025-05-26 · Zexi Li, Xiangzhu Wang, William F. Shen, Meghdad Kurmanji 외

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