English
Related papers

Related papers: BetaEdit: Null-Space Constrained Sequential Model …

200 papers

Model editing aims to precisely alter the behaviors of large language models (LLMs) in relation to specific knowledge, while leaving unrelated knowledge intact. This approach has proven effective in addressing issues of hallucination and…

Computation and Language · Computer Science 2024-09-24 Derong Xu , Ziheng Zhang , Zhihong Zhu , Zhenxi Lin , Qidong Liu , Xian Wu , Tong Xu , Wanyu Wang , Yuyang Ye , Xiangyu Zhao , Enhong Chen , Yefeng Zheng

Model editing aims to modify the outputs of large language models after they are trained. Previous approaches have often involved direct alterations to model weights, which can result in model degradation. Recent techniques avoid making…

Computation and Language · Computer Science 2025-10-10 Hammad Rizwan , Domenic Rosati , Ga Wu , Hassan Sajjad

Large language models (LLMs) encode vast world knowledge but struggle to stay up-to-date, often leading to errors and hallucinations. Knowledge editing offers an efficient alternative to retraining, enabling targeted modifications by…

Computation and Language · Computer Science 2025-06-03 Weitao Ma , Xiyuan Du , Xiaocheng Feng , Lei Huang , Yichong Huang , Huiyi Zhang , Xiaoliang Yang , Baohang Li , Xiachong Feng , Ting Liu , Bing Qin

Backtesting large language models on historical events requires reasoning exclusively from information available before a specified cutoff date. Yet models routinely leak post-cutoff knowledge from pre-training into their reasoning,…

Machine Learning · Computer Science 2026-05-20 Zeyu Zhang , Bradly C. Stadie

Unstructured Knowledge Editing (UKE) is crucial for updating the relevant knowledge of large language models (LLMs). It focuses on unstructured inputs, such as long or free-form texts, which are common forms of real-world knowledge.…

Computation and Language · Computer Science 2025-06-12 Hao Xiong , Chuanyuan Tan , Wenliang Chen

Recent advancements in diffusion-based generative image editing have sparked a profound revolution, reshaping the landscape of image outpainting and inpainting tasks. Despite these strides, the field grapples with inherent challenges,…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Yuxi Ren , Jie Wu , Yanzuo Lu , Huafeng Kuang , Xin Xia , Xionghui Wang , Qianqian Wang , Yixing Zhu , Pan Xie , Shiyin Wang , Xuefeng Xiao , Yitong Wang , Min Zheng , Lean Fu

Recent research has explored methods for updating and modifying factual knowledge in large language models, often focusing on specific multi-layer perceptron blocks. This study expands on this work by examining the effectiveness of existing…

Computation and Language · Computer Science 2025-02-05 Daniel Tamayo , Aitor Gonzalez-Agirre , Javier Hernando , Marta Villegas

A central challenge in large language model (LLM) editing is capability preservation: methods that successfully change targeted behavior can quietly game the editing proxy and corrupt general capabilities, producing degenerate behaviors…

Machine Learning · Computer Science 2026-05-05 Zarif Ikram , Arad Firouzkouhi , Stephen Tu , Mahdi Soltanolkotabi , Paria Rashidinejad

Diffusion models have revolutionized text-driven video editing. However, applying these methods to real-world editing encounters two significant challenges: (1) the rapid increase in GPU memory demand as the number of frames grows, and (2)…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Shuzhou Yang , Chong Mou , Jiwen Yu , Yuhan Wang , Xiandong Meng , Jian Zhang

Knowledge editing aims to change language models' performance on several special cases (i.e., editing scope) by infusing the corresponding expected knowledge into them. With the recent advancements in large language models (LLMs), knowledge…

Computation and Language · Computer Science 2024-05-31 Jiaan Wang , Yunlong Liang , Zengkui Sun , Yuxuan Cao , Jiarong Xu , Fandong Meng

Instruction-following image editing models are expected to modify only the specified region while keeping the rest of the image unchanged. However, in practice, we observe a pervasive phenomenon -- edit spillover: models alter semantically…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Guandong Li , Zhaobin Chu

Large Language Models (LLMs) have become indispensable tools in science, technology, and society, enabling transformative advances across diverse fields. However, errors or outdated information within these models can undermine their…

Computation and Language · Computer Science 2025-12-19 Qizhou Chen , Chengyu Wang , Taolin Zhang , Xiaofeng He

Data science pipelines to train and evaluate models with machine learning may contain bugs just like any other code. Leakage between training and test data can lead to overestimating the model's accuracy during offline evaluations, possibly…

Software Engineering · Computer Science 2022-09-08 Chenyang Yang , Rachel A Brower-Sinning , Grace A. Lewis , Christian Kästner

As the typical retraining paradigm is unacceptably time- and resource-consuming, researchers are turning to model editing to find an effective way that supports both consecutive and batch scenarios to edit the model behavior directly.…

Computation and Language · Computer Science 2024-10-14 Shuaiyi Li , Yang Deng , Deng Cai , Hongyuan Lu , Liang Chen , Wai Lam

Lifelong knowledge editing enables continuous, precise updates to outdated knowledge in large language models (LLMs) without computationally expensive full retraining. However, existing methods often accumulate errors throughout the editing…

Machine Learning · Computer Science 2025-10-28 Jinzhe Liu , Junshu Sun , Shufan Shen , Chenxue Yang , Shuhui Wang

Large Language Models (LLMs) excel in tasks such as retrieval and question answering but require updates to incorporate new knowledge and reduce inaccuracies and hallucinations. Traditional updating methods, like fine-tuning and incremental…

Computation and Language · Computer Science 2025-04-30 Yifan Wei , Xiaoyan Yu , Ran Song , Hao Peng , Angsheng Li

Query expansion methods powered by large language models (LLMs) have demonstrated effectiveness in zero-shot retrieval tasks. These methods assume that LLMs can generate hypothetical documents that, when incorporated into a query vector,…

Computation and Language · Computer Science 2025-06-05 Yejun Yoon , Jaeyoon Jung , Seunghyun Yoon , Kunwoo Park

Text-editing models have recently become a prominent alternative to seq2seq models for monolingual text-generation tasks such as grammatical error correction, simplification, and style transfer. These tasks share a common trait - they…

Data is one of the most important factors in machine learning. However, even if we have high-quality data, there is a situation in which access to the data is restricted. For example, access to the medical data from outside is strictly…

Computer Vision and Pattern Recognition · Computer Science 2018-05-29 Hyo-Eun Kim , Seungwook Kim , Jaehwan Lee

Large language models (LLMs) exhibit impressive language capabilities but remain vulnerable to malicious prompts and jailbreaking attacks. Existing knowledge editing methods for LLM detoxification face two major challenges. First, they…

Computation and Language · Computer Science 2025-05-29 Yifan Lu , Jing Li , Yigeng Zhou , Yihui Zhang , Wenya Wang , Xiucheng Li , Meishan Zhang , Fangming Liu , Jun Yu , Min Zhang