English
Related papers

Related papers: Norm Anchors Make Model Edits Last

200 papers

Although model editing has shown promise in revising knowledge in Large Language Models (LLMs), its impact on the inherent capabilities of LLMs is often overlooked. In this work, we reveal a critical phenomenon: even a single edit can…

Artificial Intelligence · Computer Science 2024-06-06 Wanli Yang , Fei Sun , Xinyu Ma , Xun Liu , Dawei Yin , Xueqi Cheng

As software projects progress, quality of code assumes paramount importance as it affects reliability, maintainability and security of software. For this reason, static analysis tools are used in developer workflows to flag code quality…

Recently, large language models (LLMs) have demonstrated impressive results but still suffer from hallucinations. Model editing has been proposed to correct factual inaccuracies in LLMs. A challenging case is sequential model editing (SME),…

Computation and Language · Computer Science 2025-06-24 Taolin Zhang , Haidong Kang , Dongyang Li , Qizhou Chen , Chengyu Wang Xiaofeng He , Richang Hong

Large Language Models (LLMs) are highly vulnerable to input perturbations, as even a small prompt change may result in a substantially different output. Existing methods to enhance LLM robustness are primarily focused on perturbed data…

Computation and Language · Computer Science 2025-04-04 Aryan Agrawal , Lisa Alazraki , Shahin Honarvar , Marek Rei

Model editing is an emerging field that focuses on updating the knowledge embedded within large language models (LLMs) without extensive retraining. However, current model editing methods significantly compromise the general abilities of…

Computation and Language · Computer Science 2025-03-04 Jun-Yu Ma , Hong Wang , Hao-Xiang Xu , Zhen-Hua Ling , Jia-Chen Gu

Knowledge editing aims to efficiently modify the internal knowledge of large language models (LLMs) without compromising their other capabilities. The prevailing editing paradigm, which appends an update matrix to the original parameter…

Machine Learning · Computer Science 2026-01-14 Hao-Xiang Xu , Jun-Yu Ma , Ziqi Peng , Yuhao Sun , Zhen-Hua Ling , Jia-Chen Gu

Existing approaches typically rely on fixed length penalties, but such penalties are hard to tune and fail to adapt to the evolving reasoning abilities of LLMs, leading to suboptimal trade-offs between accuracy and conciseness. To address…

Artificial Intelligence · Computer Science 2025-12-29 Yanhao Li , Lu Ma , Jiaran Zhang , Lexiang Tang , Wentao Zhang , Guibo Luo

NLP benchmarks rely on standardized datasets for training and evaluating models and are crucial for advancing the field. Traditionally, expert annotations ensure high-quality labels; however, the cost of expert annotation does not scale…

Computation and Language · Computer Science 2025-09-15 Omer Nahum , Nitay Calderon , Orgad Keller , Idan Szpektor , Roi Reichart

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…

Computation and Language · Computer Science 2025-10-02 Bhiman Kumar Baghel , Emma Jordan , Zheyuan Ryan Shi , Xiang Lorraine Li

Real-world machine learning applications often struggle with two major challenges: distribution shift and label noise. Models tend to overfit by focusing on redundant and uninformative features in the training data, which makes it hard for…

Computation and Language · Computer Science 2025-04-22 Zilin Dai , Lehong Wang , Fangzhou Lin , Yidong Wang , Zhigang Li , Kazunori D Yamada , Ziming Zhang , Wang Lu

Regression under uncertainty is fundamental across science and engineering. We present an Anchored Mixture of Experts (Anchor-MoE), a model that handles both probabilistic and point regression. For simplicity, we use a tuned…

Machine Learning · Computer Science 2025-08-26 Baozhuo Su , Zhengxian Qu

Large Language Models (LLMs) are regularly updated to enhance performance, typically through changes in data or architecture. Within the update process, developers often prioritize improving overall performance metrics, paying less…

Artificial Intelligence · Computer Science 2024-10-07 Jessica Echterhoff , Fartash Faghri , Raviteja Vemulapalli , Ting-Yao Hu , Chun-Liang Li , Oncel Tuzel , Hadi Pouransari

The acceleration of Large Language Models (LLMs) research has opened up new possibilities for evaluating generated texts. They serve as scalable and economical evaluators, but the question of how reliable these evaluators are has emerged as…

Computation and Language · Computer Science 2024-12-10 Minzhi Li , Zhengyuan Liu , Shumin Deng , Shafiq Joty , Nancy F. Chen , Min-Yen Kan

Large language models (LLMs) have shown great success in various Natural Language Processing (NLP) tasks, whist they still need updates after deployment to fix errors or keep pace with the changing knowledge in the world. Researchers…

Computation and Language · Computer Science 2023-12-20 Lang Yu , Qin Chen , Jie Zhou , Liang He

Given the success of Large Language Models (LLMs), there has been considerable interest in studying the properties of model activations. The literature overwhelmingly agrees that LLM representations are dominated by a few "outlier…

Computation and Language · Computer Science 2024-04-05 William Rudman , Carsten Eickhoff

Synthetically-generated data plays an increasingly larger role in training large language models. However, while synthetic data has been found to be useful, studies have also shown that without proper curation it can cause LLM performance…

Machine Learning · Computer Science 2025-12-02 Kareem Amin , Sara Babakniya , Alex Bie , Weiwei Kong , Umar Syed , Sergei Vassilvitskii

LLM-based automated program repair (APR) techniques have shown promising results in reducing debugging costs. However, prior results can be affected by data leakage: large language models (LLMs) may memorize bug fixes when evaluation…

Software Engineering · Computer Science 2026-04-24 Milan De Koning , Ali Asgari , Pouria Derakhshanfar , Annibale Panichella

Finetuning large language models (LLMs) enables user-specific customization but introduces critical safety risks: even a few harmful examples can compromise safety alignment. A common mitigation strategy is to update the model more strongly…

Machine Learning · Computer Science 2025-12-23 ShengYun Peng , Pin-Yu Chen , Jianfeng Chi , Seongmin Lee , Duen Horng Chau

Deep supervised learning has achieved remarkable success across a wide range of tasks, yet it remains susceptible to overfitting when confronted with noisy labels. To address this issue, noise-robust loss functions offer an effective…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Xichen Ye , Yifan Wu , Yiqi Wang , Xiaoqiang Li , Weizhong Zhang , Yifan Chen

Large Language Models (LLMs) excel at rewriting tasks such as text style transfer and grammatical error correction. While there is considerable overlap between the inputs and outputs in these tasks, the decoding cost still increases with…

Computation and Language · Computer Science 2025-01-24 Hao Zhang , Felix Stahlberg , Shankar Kumar