English
Related papers

Related papers: Does Localization Inform Editing? Surprising Diffe…

200 papers

As Large language models (LLMs) are increasingly deployed in diverse applications, faithfully integrating evolving factual knowledge into these models remains a critical challenge. Continued pre-training on paraphrased data has shown…

Computation and Language · Computer Science 2025-06-24 Mingkang Zhu , Xi Chen , Zhongdao Wang , Bei Yu , Hengshuang Zhao , Jiaya Jia

Current pre-trained language models have enabled remarkable improvements in downstream tasks, but it remains difficult to distinguish effects of statistical correlation from more systematic logical reasoning grounded on understanding of the…

Computation and Language · Computer Science 2022-12-08 Jiaxuan Li , Lang Yu , Allyson Ettinger

Overparameterized deep networks that generalize well have been key to the dramatic success of deep learning in recent years. The reasons for their remarkable ability to generalize are not well understood yet. When class labels in the…

Machine Learning · Computer Science 2026-02-03 Simran Ketha , Venkatakrishnan Ramaswamy

Novel diffusion models can synthesize photo-realistic images with integrated high-quality text. Surprisingly, we demonstrate through attention activation patching that only less than $1$% of diffusion models' parameters, all contained in…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Łukasz Staniszewski , Bartosz Cywiński , Franziska Boenisch , Kamil Deja , Adam Dziedzic

Language Models (LMs) may acquire harmful knowledge, and yet feign ignorance of these topics when under audit. Inspired by the recent discovery of deception-related behaviour patterns in LMs, we aim to train classifiers that detect when a…

Computation and Language · Computer Science 2026-03-24 Dhananjay Ashok , Ruth-Ann Armstrong , Jonathan May

As the world changes, we need to be able to update our models and correct false information without costly retraining. Knowledge-based model editing enables precise modifications to the weights of large language models in order to modify…

Machine Learning · Computer Science 2025-02-28 Elan Markowitz , Anil Ramakrishna , Ninareh Mehrabi , Charith Peris , Rahul Gupta , Kai-Wei Chang , Aram Galstyan

Large Language Models store extensive factual knowledge acquired during large-scale pre-training. However, this knowledge is inherently static, reflecting only the state of the world at the time of training. Knowledge editing has emerged as…

Computation and Language · Computer Science 2025-10-14 Geunyeong Jeong , Juoh Sun , Seonghee Lee , Harksoo Kim

Large language models (LLMs) are typically trained on shuffled corpora, yielding models whose knowledge is frozen at train time and whose temporal grounding remains poorly understood. In this work, we study the impact of pre-training…

Computation and Language · Computer Science 2026-05-26 Hippolyte Pilchen , Romain Fabre , Franck Signe Talla , Patrick Perez , Edouard Grave

Large language models (LLMs) inevitably encode outdated or incorrect knowledge. Updating, deleting, and forgetting such knowledge is important for alignment, safety, and other issues. To address this issue, model editing has emerged as a…

Artificial Intelligence · Computer Science 2025-10-02 Wei Liu , Haomei Xu , Bingqing Liu , Zhiying Deng , Haozhao Wang , Jun Wang , Ruixuan Li , Yee Whye Teh , Wee Sun Lee

In this work, we study the impact of QA fine-tuning data on downstream factuality. We show that fine-tuning on lesser-known facts that are poorly stored during pretraining yields significantly worse factuality than fine-tuning on well-known…

Computation and Language · Computer Science 2024-06-24 Gaurav Ghosal , Tatsunori Hashimoto , Aditi Raghunathan

Modern language models have the capacity to store and use immense amounts of knowledge about real-world entities, but it remains unclear how to update such knowledge stored in model parameters. While prior methods for updating knowledge in…

Computation and Language · Computer Science 2023-11-01 Shankar Padmanabhan , Yasumasa Onoe , Michael J. Q. Zhang , Greg Durrett , Eunsol Choi

Model editing aims at selectively updating a small subset of a neural model's parameters with an interpretable strategy to achieve desired modifications. It can significantly reduce computational costs to adapt to large language models…

Computation and Language · Computer Science 2025-03-20 Shichen Li , Zhongqing Wang , Zheyu Zhao , Yue Zhang , Peifeng Li

While large language models are able to retain vast amounts of world knowledge seen during pretraining, such knowledge is prone to going out of date and is nontrivial to update. Furthermore, these models are often used under temporal…

Computation and Language · Computer Science 2024-03-06 Michael J. Q. Zhang , Eunsol Choi

Large Language Models (LLMs) have demonstrated remarkable efficiency in tackling various tasks based on human instructions, but studies reveal that they often struggle with tasks requiring reasoning, such as math or physics. This limitation…

Computation and Language · Computer Science 2024-10-08 Ruoyu Wang , Xiaoxuan Li , Lina Yao

Public datasets are often used to evaluate the efficacy and generalizability of state-of-the-art methods for many tasks in natural language processing (NLP). However, the presence of overlap between the train and test datasets can lead to…

Computation and Language · Computer Science 2021-02-04 Aparna Elangovan , Jiayuan He , Karin Verspoor

Protecting privacy in contemporary NLP models is gaining in importance. So does the need to mitigate social biases of such models. But can we have both at the same time? Existing research suggests that privacy preservation comes at the…

Computation and Language · Computer Science 2023-05-25 Cleo Matzken , Steffen Eger , Ivan Habernal

While existing evaluations of large language models (LLMs) measure deception rates, the underlying conditions that give rise to deceptive behavior are poorly understood. We investigate this question using a novel dataset of realistic moral…

Large language models are typically trained by treating text as a single global distribution, often resulting in geographically homogenized behavior. We study metadata conditioning as a lightweight approach for localization, pre-training 31…

Computation and Language · Computer Science 2026-01-22 Anjishnu Mukherjee , Ziwei Zhu , Antonios Anastasopoulos

Knowledge editing methods such as ROME and MEMIT update factual associations in transformer models by modifying MLP weights. While evaluated mainly by output behavior, their internal mechanism remains underexplored. We investigate whether…

Machine Learning · Computer Science 2026-05-29 Ali Holmov , Paul Youssef , Nandi Schoots , Christin Seifert

Language Generation Models produce words based on the previous context. Although existing methods offer input attributions as explanations for a model's prediction, it is still unclear how prior words affect the model's decision throughout…

Computation and Language · Computer Science 2023-05-23 Javier Ferrando , Gerard I. Gállego , Ioannis Tsiamas , Marta R. Costa-jussà