English
Related papers

Related papers: Has this Fact been Edited? Detecting Knowledge Edi…

200 papers

Large Language Models (LLMs) require continuous updates to maintain accurate and current knowledge as the world evolves. While existing knowledge editing approaches offer various solutions for knowledge updating, they often struggle with…

Artificial Intelligence · Computer Science 2025-06-17 Zichuan Fu , Xian Wu , Guojing Li , Yingying Zhang , Yefeng Zheng , Tianshi Ming , Yejing Wang , Wanyu Wang , Xiangyu Zhao

We propose a method to determine whether a given article was written entirely by a generative language model or perhaps contains edits by a different author, possibly a human. Our process involves multiple tests for the origin of individual…

Information Theory · Computer Science 2024-08-27 Idan Kashtan , Alon Kipnis

Machine unlearning has emerged as a prevalent technical solution for selectively removing unwanted knowledge absorbed during pre-training, without requiring full retraining. While recent unlearning techniques can effectively remove…

Machine Learning · Computer Science 2025-11-04 Myeongseob Ko , Hoang Anh Just , Charles Fleming , Ming Jin , Ruoxi Jia

Efficient knowledge editing of large language models is crucial for replacing obsolete information or incorporating specialized knowledge on a large scale. However, previous methods implicitly assume that knowledge is localized and isolated…

Computation and Language · Computer Science 2024-02-21 Zihao Wei , Liang Pang , Hanxing Ding , Jingcheng Deng , Huawei Shen , Xueqi Cheng

Knowledge-enhanced Pre-trained Language Model (PLM) has recently received significant attention, which aims to incorporate factual knowledge into PLMs. However, most existing methods modify the internal structures of fixed types of PLMs by…

Computation and Language · Computer Science 2022-10-18 Jianing Wang , Wenkang Huang , Qiuhui Shi , Hongbin Wang , Minghui Qiu , Xiang Li , Ming Gao

Previous studies have shown that large language models (LLMs) like GPTs store massive factual knowledge in their parameters. However, the stored knowledge could be false or out-dated. Traditional knowledge editing methods refine LLMs via…

Computation and Language · Computer Science 2023-05-23 Ce Zheng , Lei Li , Qingxiu Dong , Yuxuan Fan , Zhiyong Wu , Jingjing Xu , Baobao Chang

In-context knowledge editing (IKE) is a promising technique for updating Large Language Models (LLMs) with new information. However, IKE relies on lengthy, fact-specific demonstrations which are costly to create and consume significant…

Computation and Language · Computer Science 2026-01-27 Paul Youssef , Christin Seifert , Jörg Schlötterer

During pre-training, the Text-to-Image (T2I) diffusion models encode factual knowledge into their parameters. These parameterized facts enable realistic image generation, but they may become obsolete over time, thereby misrepresenting the…

Computation and Language · Computer Science 2024-10-29 Hengrui Gu , Kaixiong Zhou , Yili Wang , Ruobing Wang , Xin Wang

As real-world knowledge evolves, the information embedded within large language models (LLMs) can become outdated, inadequate, or erroneous. Model editing has emerged as a prominent approach for updating LLMs' knowledge with minimal…

Computation and Language · Computer Science 2025-03-10 Guoxiu He , Xin Song , Aixin Sun

Knowledge editing enables multimodal large language models (MLLMs) to efficiently update outdated or incorrect information. However, existing benchmarks primarily emphasize cognitive-level modifications while lacking a focus on deeper…

Artificial Intelligence · Computer Science 2025-09-09 Zhaoyu Fan , Kaihang Pan , Mingze Zhou , Bosheng Qin , Juncheng Li , Shengyu Zhang , Wenqiao Zhang , Siliang Tang , Fei Wu , Yueting Zhuang

Language models (LMs) are sentence-completion engines trained on massive corpora. LMs have emerged as a significant breakthrough in natural-language processing, providing capabilities that go far beyond sentence completion including…

Artificial Intelligence · Computer Science 2021-10-26 Robert E. Wray , III , James R. Kirk , John E. Laird

Language models learn a great quantity of factual information during pretraining, and recent work localizes this information to specific model weights like mid-layer MLP weights. In this paper, we find that we can change how a fact is…

Machine Learning · Computer Science 2023-10-17 Peter Hase , Mohit Bansal , Been Kim , Asma Ghandeharioun

Knowledge enhanced pre-trained language models (K-PLMs) are shown to be effective for many public tasks in the literature but few of them have been successfully applied in practice. To address this problem, we propose K-AID, a systematic…

Artificial Intelligence · Computer Science 2021-09-23 Fu Sun , Feng-Lin Li , Ruize Wang , Qianglong Chen , Xingyi Cheng , Ji Zhang

Model editing has emerged as a cost-effective strategy to update knowledge stored in language models. However, model editing can have unintended consequences after edits are applied: information unrelated to the edits can also be changed,…

Computation and Language · Computer Science 2024-10-07 Karina Halevy , Anna Sotnikova , Badr AlKhamissi , Syrielle Montariol , Antoine Bosselut

Large Language Models (LLMs) require efficient knowledge editing (KE) to update factual information, yet existing methods exhibit significant performance decay in multi-hop factual recall. This failure is particularly acute when edits…

Computation and Language · Computer Science 2026-03-10 Jiayu Yang , Yuxuan Fan , Songning Lai , Shengen Wu , Jiaqi Tang , Chun Kang , Zhijiang Guo , Yutao Yue

Knowledge embeddings (KE) represent a knowledge graph (KG) by embedding entities and relations into continuous vector spaces. Existing methods are mainly structure-based or description-based. Structure-based methods learn representations…

Computation and Language · Computer Science 2023-06-30 Xintao Wang , Qianyu He , Jiaqing Liang , Yanghua Xiao

The knowledge within large language models (LLMs) may become outdated quickly. While in-context editing (ICE) is currently the most effective method for knowledge editing (KE), it is constrained by the black-box modeling of LLMs and thus…

Computation and Language · Computer Science 2024-05-22 Baolong Bi , Shenghua Liu , Lingrui Mei , Yiwei Wang , Pengliang Ji , Xueqi Cheng

Pre-trained Language Models (PLMs) encode various facts about the world at their pre-training phase as they are trained to predict the next or missing word in a sentence. There has a been an interest in quantifying and improving the amount…

Computation and Language · Computer Science 2024-10-18 Paul Youssef , Jörg Schlötterer , Christin Seifert

Knowledge editing aims to correct outdated or inaccurate knowledge in neural networks. In this paper, we explore knowledge editing using easily accessible documents instead of manually labeled factual triples employed in earlier research.…

Computation and Language · Computer Science 2025-07-25 Suhang Wu , Ante Wang , Minlong Peng , Yujie Lin , Wenbo Li , Mingming Sun , Jinsong Su

Knowledge editing aims to efficiently correct factual errors in language models. Widely used locate-then-edit methods update an MLP layer by adjusting its weights to change the mapping between the layer's input vector (key) and output…

Computation and Language · Computer Science 2026-03-03 Haewon Park , Sangwoo Kim , Yohan Jo