English
Related papers

Related papers: Does Localization Inform Editing? Surprising Diffe…

200 papers

Large Audio-Language Models (LALMs) have shown strong performance in speech understanding, making speech a natural interface for accessing factual information. Yet they are trained on static corpora and may encode incorrect facts. Existing…

Machine Learning · Computer Science 2026-03-17 Sung Kyun Chung , Jiaheng Dong , Qiuchi Hu , Gongping Huang , Hong Jia , Ting Dang

Large language models encapsulate knowledge and have demonstrated superior performance on various natural language processing tasks. Recent studies have localized this knowledge to specific model parameters, such as the MLP weights in…

Computation and Language · Computer Science 2024-09-04 Yifan Wei , Xiaoyan Yu , Yixuan Weng , Huanhuan Ma , Yuanzhe Zhang , Jun Zhao , Kang Liu

A basic aspiration for interpretability research in large language models is to "localize" semantically meaningful behaviors to particular components within the LLM. There are various heuristics for finding candidate locations within the…

Machine Learning · Computer Science 2025-02-20 Zihao Wang , Victor Veitch

Identifying layers within text-to-image models which control visual attributes can facilitate efficient model editing through closed-form updates. Recent work, leveraging causal tracing show that early Stable-Diffusion variants confine…

Computer Vision and Pattern Recognition · Computer Science 2024-05-09 Samyadeep Basu , Keivan Rezaei , Priyatham Kattakinda , Ryan Rossi , Cherry Zhao , Vlad Morariu , Varun Manjunatha , Soheil Feizi

Methods for knowledge editing and unlearning in large language models seek to edit or remove undesirable knowledge or capabilities without compromising general language modeling performance. This work investigates how mechanistic…

Machine Learning · Computer Science 2024-12-06 Phillip Guo , Aaquib Syed , Abhay Sheshadri , Aidan Ewart , Gintare Karolina Dziugaite

Large Language Model (LLM) editing modifies factual information in LLMs. Locate-and-Edit (L\&E) methods accomplish this by finding where relevant information is stored within the neural network, and editing the weights at that location. The…

Computation and Language · Computer Science 2024-01-17 Itai Feigenbaum , Devansh Arpit , Huan Wang , Shelby Heinecke , Juan Carlos Niebles , Weiran Yao , Caiming Xiong , Silvio Savarese

The potential of using a large language model (LLM) as a knowledge base (KB) has sparked significant interest. To manage the knowledge acquired by LLMs, we need to ensure that the editing of learned facts respects internal logical…

Computation and Language · Computer Science 2023-12-05 Zichao Li , Ines Arous , Siva Reddy , Jackie C. K. Cheung

Knowledge editing aims to update outdated information in Large Language Models (LLMs). A representative line of study is locate-then-edit methods, which typically employ causal tracing to identify the modules responsible for recalling…

Computation and Language · Computer Science 2025-03-18 Haowen Pan , Xiaozhi Wang , Yixin Cao , Zenglin Shi , Xun Yang , Juanzi Li , Meng Wang

Large language models often retain unintended content, prompting growing interest in knowledge unlearning. Recent approaches emphasize localized unlearning, restricting parameter updates to specific regions in an effort to remove target…

Computation and Language · Computer Science 2026-02-12 Hwiyeong Lee , Uiji Hwang , Hyelim Lim , Taeuk Kim

We characterize how memorization is represented in transformer models and show that it can be disentangled in the weights of both language models (LMs) and vision transformers (ViTs) using a decomposition based on the loss landscape…

Computation and Language · Computer Science 2025-11-03 Jack Merullo , Srihita Vatsavaya , Lucius Bushnaq , Owen Lewis

Knowledge editing, which aims to update the knowledge encoded in language models, can be deceptive. Despite the fact that many existing knowledge editing algorithms achieve near-perfect performance on conventional metrics, the models edited…

Computation and Language · Computer Science 2025-05-20 Jiakuan Xie , Pengfei Cao , Yubo Chen , Kang Liu , Jun Zhao

Large Language Models (LLMs) trained on web-scale text corpora have been shown to capture world knowledge in their parameters. However, the mechanism by which language models store different types of knowledge is poorly understood. In this…

Computation and Language · Computer Science 2024-11-08 Jared Fernandez , Yonatan Bisk , Emma Strubell

Knowledge editing methods (KEs) can update language models' obsolete or inaccurate knowledge learned from pre-training. However, KEs can be used for malicious applications, e.g., inserting misinformation and toxic content. Knowing whether a…

Computation and Language · Computer Science 2025-02-11 Paul Youssef , Zhixue Zhao , Christin Seifert , Jörg Schlötterer

Memorisation is a natural part of learning from real-world data: neural models pick up on atypical input-output combinations and store those training examples in their parameter space. That this happens is well-known, but how and where are…

Computation and Language · Computer Science 2024-08-12 Verna Dankers , Ivan Titov

Can we localize the weights and mechanisms used by a language model to memorize and recite entire paragraphs of its training data? In this paper, we show that while memorization is spread across multiple layers and model components,…

Computation and Language · Computer Science 2024-04-01 Niklas Stoehr , Mitchell Gordon , Chiyuan Zhang , Owen Lewis

Existing methods in Multimodal Knowledge Editing (MKE) have advanced the ability to correct outdated or inaccurate knowledge in Multimodal Large Language Models (MLLMs). However, they exhibit a critical limitation: while effectively…

Computation and Language · Computer Science 2026-05-29 Leijiang Gu , Zhen Zeng , Feng Li , Xinjian Gao , Zenglin Shi

The storage and recall of factual associations in auto-regressive transformer language models (LMs) have drawn a great deal of attention, inspiring knowledge editing by directly modifying the located model weights. Most editing works…

Computation and Language · Computer Science 2025-02-28 Xiyu Liu , Zhengxiao Liu , Naibin Gu , Zheng Lin , Wanli Ma , Ji Xiang , Weiping Wang

The factual knowledge acquired during pre-training and stored in the parameters of Language Models (LMs) can be useful in downstream tasks (e.g., question answering or textual inference). However, some facts can be incorrectly induced or…

Computation and Language · Computer Science 2021-09-10 Nicola De Cao , Wilker Aziz , Ivan Titov

Large language models store not only isolated facts but also rules that support reasoning across symbolic expressions, natural language explanations, and concrete instances. Yet most model editing methods are built for fact-level knowledge,…

Computation and Language · Computer Science 2026-04-10 Yating Wang , Wenting Zhao , Yaqi Zhao , Yongshun Gong , Yilong Yin , Haoliang Sun

The concept of localization in LLMs is often mentioned in prior work; however, methods for localization have never been systematically and directly evaluated. We propose two complementary benchmarks that evaluate the ability of localization…

Computation and Language · Computer Science 2024-04-03 Ting-Yun Chang , Jesse Thomason , Robin Jia
‹ Prev 1 2 3 10 Next ›