中文
相关论文

相关论文: UltraEdit: Training-, Subject-, and Memory-Free Li…

200 篇论文

Large language models (LLMs) acquire information from pre-training corpora, but their stored knowledge can become inaccurate or outdated over time. Model editing addresses this challenge by modifying model parameters without retraining, and…

计算与语言 · 计算机科学 2025-09-09 Zherui Li , Houcheng Jiang , Hao Chen , Baolong Bi , Zhenhong Zhou , Fei Sun , Junfeng Fang , Xiang Wang

Large language models (LLMs) require frequent knowledge updates to reflect changing facts and mitigate hallucinations. To meet this demand, lifelong knowledge editing has emerged as a continual approach to modify specific pieces of…

人工智能 · 计算机科学 2026-04-22 Dahyun Jung , Jaewook Lee , Heuiseok Lim

Model editing aims to correct inaccurate knowledge, update outdated information, and incorporate new data into Large Language Models (LLMs) without the need for retraining. This task poses challenges in lifelong scenarios where edits must…

计算与语言 · 计算机科学 2025-03-17 Qizhou Chen , Chengyu Wang , Dakan Wang , Taolin Zhang , Wangyue Li , Xiaofeng He

Model editing aims to enhance the accuracy and reliability of large language models (LLMs) by efficiently adjusting their internal parameters. Currently, most LLM editing datasets are confined to narrow knowledge domains and cover a limited…

计算与语言 · 计算机科学 2025-11-12 Qizhou Chen , Dakan Wang , Taolin Zhang , Zaoming Yan , Chengsong You , Chengyu Wang , Xiaofeng He

Adjusting the outdated knowledge of large language models (LLMs) after deployment remains a major challenge. This difficulty has spurred the development of knowledge editing, which seeks to accurately and efficiently modify a model's…

计算与语言 · 计算机科学 2025-12-05 Pengfei Cao , Zeao Ji , Daojian Zeng , Jun Zhao , Kang Liu

Instruction-based text editing is increasingly critical for real-world applications such as code editors (e.g., Cursor), but Large Language Models (LLMs) continue to struggle with this task. Unlike free-form generation, editing requires…

计算与语言 · 计算机科学 2025-12-16 Yiming Zeng , Jinghan Cao , Zexin Li , Wanhao Yu , Zhankai Ye , Dawei Xiang , Ting Hua , Xin Liu , Shangqian Gao , Tingting Yu

Lifelong model editing (LME) aims to sequentially rectify outdated or inaccurate knowledge in deployed LLMs while minimizing side effects on unrelated inputs. However, existing approaches typically apply parameter perturbations to a static…

计算与语言 · 计算机科学 2026-04-14 Yangfan Wang , Tianyang Sun , Chen Tang , Jie Liu , Wei Cai , Jingchi Jiang

Large Language Models (LLMs) have shown extraordinary capabilities in understanding and generating text that closely mirrors human communication. However, a primary limitation lies in the significant computational demands during training,…

Large language models (LLMs) acquire knowledge during pre-training, but over time, this knowledge may become incorrect or outdated, necessitating updates after training. Knowledge editing techniques address this issue without the need for…

计算与语言 · 计算机科学 2024-10-16 Yuchen Cai , Ding Cao

This paper presents UltraEdit, a large-scale (approximately 4 million editing samples), automatically generated dataset for instruction-based image editing. Our key idea is to address the drawbacks in existing image editing datasets like…

计算机视觉与模式识别 · 计算机科学 2024-12-20 Haozhe Zhao , Xiaojian Ma , Liang Chen , Shuzheng Si , Rujie Wu , Kaikai An , Peiyu Yu , Minjia Zhang , Qing Li , Baobao Chang

Large Language Models (LLMs) usually suffer from knowledge cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect facts owing to outdated/noisy data. To this end, many knowledge editing…

Language models deployed in real-world systems often require post-hoc updates to incorporate new or corrected knowledge. However, editing such models efficiently and reliably-without retraining or forgetting previous information-remains a…

计算与语言 · 计算机科学 2026-02-03 Ke Wang , Yiming Qin , Nikolaos Dimitriadis , Alessandro Favero , Pascal Frossard

Large Language Models (LLMs) are widely deployed in downstream tasks, but keeping their knowledge up-to-date via retraining or fine-tuning is often computationally expensive. Model editing provides a more efficient alternative by updating a…

计算与语言 · 计算机科学 2025-10-02 Bhiman Kumar Baghel , Emma Jordan , Zheyuan Ryan Shi , Xiang Lorraine Li

Efficiently updating multilingual knowledge in large language models (LLMs), while preserving consistent factual representations across languages, remains a long-standing and unresolved challenge. While deploying separate editing systems…

计算与语言 · 计算机科学 2025-06-13 Wei Sun , Tingyu Qu , Mingxiao Li , Jesse Davis , Marie-Francine Moens

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…

Large language models (LLMs) need knowledge updates to meet the ever-growing world facts and correct the hallucinated responses, facilitating the methods of lifelong model editing. Where the updated knowledge resides in memories is a…

计算与语言 · 计算机科学 2024-12-20 Peng Wang , Zexi Li , Ningyu Zhang , Ziwen Xu , Yunzhi Yao , Yong Jiang , Pengjun Xie , Fei Huang , Huajun Chen

Lifelong Model Editing aims to continuously update evolving facts in Large Language Models while preserving unrelated knowledge and general capabilities, yet it remains plagued by catastrophic forgetting and model collapse. Empirically, we…

机器学习 · 计算机科学 2026-05-13 Xin Ma , Wei Chen , Qi Liu , Derong Xu , Zhi Zheng , Tong Xu , Enhong Chen

Keeping large language models factually up-to-date is crucial for deployment, yet costly retraining remains a challenge. Knowledge editing offers a promising alternative, but methods are only tested on small-scale or synthetic edit…

计算与语言 · 计算机科学 2025-09-23 Lukas Thede , Karsten Roth , Matthias Bethge , Zeynep Akata , Tom Hartvigsen

Model editing techniques are essential for efficiently updating knowledge in large language models (LLMs). However, the effectiveness of existing approaches degrades in massive editing scenarios, particularly when evaluated with practical…

计算与语言 · 计算机科学 2026-02-25 Yanbo Dai , Zhenlan Ji , Zongjie Li , Shuai Wang

Large language models (LLMs) often produce incorrect or outdated information, necessitating efficient and precise knowledge updates. Current model editing methods, however, struggle with long-form knowledge in diverse formats, such as…

计算与语言 · 计算机科学 2025-10-13 Houcheng Jiang , Junfeng Fang , Ningyu Zhang , Guojun Ma , Mingyang Wan , Xiang Wang , Xiangnan He , Tat-seng Chua
‹ 上一页 1 2 3 10 下一页 ›