English
Related papers

Related papers: Norm Anchors Make Model Edits Last

200 papers

Large language models (LLMs) inevitably encode outdated or incorrect knowledge.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

Large language models (LLMs) often exhibit hallucinations due to incorrect or outdated knowledge. Hence, model editing methods have emerged to enable targeted knowledge updates. To achieve this, a prevailing paradigm is the…

Computation and Language · Computer Science 2025-04-23 Junfeng Fang , Houcheng Jiang , Kun Wang , Yunshan Ma , Shi Jie , Xiang Wang , Xiangnan He , Tat-seng Chua

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…

Artificial Intelligence · Computer Science 2026-04-22 Dahyun Jung , Jaewook Lee , Heuiseok Lim

Looped Language Models (LoopLMs) enable efficient latent reasoning through depth recurrence, yet exhibit unreliable test-time scaling behavior: performance often peaks at a certain iteration depth and then collapses with further recurrence.…

Machine Learning · Computer Science 2026-05-27 Xiao-Wen Yang , Ziyu Han , Xi-Hua Zhang , Wen-Da Wei , Jie-Jing Shao , Lan-Zhe Guo , Yu-Feng Li

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) now write code in settings where misreading a single word can break safety or cost money, yet we still expect them to overlook stray typos. To probe where useful robustness ends and harmful insensitivity begins,…

Computation and Language · Computer Science 2025-07-23 Altynbek Ismailov , Salia Asanova

Large Language Models (LLMs) power numerous AI applications, yet updating their knowledge remains costly. Model editing provides a lightweight alternative through targeted parameter modifications, with meta-learning-based model editing…

Computation and Language · Computer Science 2026-01-30 Xiaopeng Li , Shasha Li , Xi Wang , Shezheng Song , Bin Ji , Shangwen Wang , Jun Ma , Xiaodong Liu , Mina Liu , Jie Yu

This work introduces a novel framework for evaluating LLMs' capacity to balance instruction-following with critical reasoning when presented with multiple-choice questions containing no valid answers. Through systematic evaluation across…

Computation and Language · Computer Science 2025-06-03 Gracjan Góral , Emilia Wiśnios , Piotr Sankowski , Paweł Budzianowski

Large Audio-Language Models (LALMs) have shown strong performance in speech understanding, making speech a natural interface for accessing factual information. Yet they are trained on static corpora and may encode incorrect facts. Existing…

Machine Learning · Computer Science 2026-03-17 Sung Kyun Chung , Jiaheng Dong , Qiuchi Hu , Gongping Huang , Hong Jia , Ting Dang

Knowledge editing is a promising way to improve factuality in large language models, but recent studies have shown significant model degradation during sequential editing. In this paper, we formalize the popular locate-then-edit methods as…

Computation and Language · Computer Science 2025-05-22 Akshat Gupta , Phudish Prateepamornkul , Maochuan Lu , Ahmed Alaa , Thomas Hartvigsen , Gopala Anumanchipalli

In LLM training, normalization layers and optimizers are typically treated as independent design choices. In a 3x2 factorial at 1B parameters and 1000 training steps, we show this assumption can fail: Dynamic Erf (Derf; Chen & Liu, 2025)…

Artificial Intelligence · Computer Science 2026-04-03 Abdelrahman Abouzeid

Iterative self-correction is increasingly deployed in agentic LLM systems, yet whether repeated refinement improves or degrades performance remains inconsistent across models. We recast self-correction as a closed-loop feedback-control…

Artificial Intelligence · Computer Science 2026-05-05 Aofan Liu , Jingxiang Meng

Safety-aligned large language models (LLMs) remain vulnerable to backdoor attacks. Recent model editing-based approaches enable efficient backdoor injection by directly modifying a small set of parameters to map triggers to attacker-desired…

Computation and Language · Computer Science 2026-03-25 Houcheng Jiang , Zetong Zhao , Junfeng Fang , Haokai Ma , Ruipeng Wang , Xiang Wang , Xiangnan He , Yang Deng

Large Language Models (LLMs) are rarely static and are frequently updated in practice. A growing body of alignment research has shown that models initially deemed "aligned" can exhibit misaligned behavior after fine-tuning, such as…

Machine Learning · Computer Science 2026-02-02 Yavuz Bakman , Duygu Nur Yaldiz , Salman Avestimehr , Sai Praneeth Karimireddy

"LLM-as-a-judge," which utilizes large language models (LLMs) as evaluators, has proven effective in many evaluation tasks. However, evaluator LLMs exhibit numerical bias, a phenomenon where certain evaluation scores are generated…

Computation and Language · Computer Science 2026-01-27 Ayako Sato , Hwichan Kim , Zhousi Chen , Masato Mita , Mamoru Komachi

Large language models (LLMs) require continual updates to rectify outdated or erroneous knowledge. Model editing has emerged as a compelling paradigm for introducing targeted modifications without the computational burden of full…

Computation and Language · Computer Science 2026-04-07 Sicheng Lyu , Yu Gu , Xinyu Wang , Jerry Huang , Sitao Luan , Yufei Cui , Xiao-Wen Chang , Peng Lu

Reinforcement learning with verifiable rewards (RLVR) has become a highly effective method for improving the reasoning abilities of Large Language Models (LLMs). Recent research shows that Negative Sample Reinforcement (NSR) -- which…

Machine Learning · Computer Science 2026-05-11 Yash Ingle , Jaival Chauhan , Ankit Yadav , Sudhakar Mishra

Test-Time Scaling (TTS) has significantly enhanced the capabilities of Large Reasoning Models (LRMs) but introduces a critical side-effect known as Overthinking. We conduct a preliminary study to rethink this phenomenon from a fine-grained…

Computation and Language · Computer Science 2026-02-10 Kaiyan Chang , Chenwei Zhu , Yingfeng Luo , Yifu Huo , Chenglong Wang , Xiaoqian Liu , Qiaozhi He , Tong Xiao , Zhengtao Yu , Jingbo Zhu

Large Language Model (LLM) editing modifies factual information in LLMs. Locate-and-Edit (L\&E) methods accomplish this by finding where relevant information is stored within the neural network, and editing the weights at that location. The…

Computation and Language · Computer Science 2024-01-17 Itai Feigenbaum , Devansh Arpit , Huan Wang , Shelby Heinecke , Juan Carlos Niebles , Weiran Yao , Caiming Xiong , Silvio Savarese

Large language models (LLMs) require constant updates to remain aligned with evolving real-world knowledge. Model editing offers a lightweight alternative to retraining, but sequential editing often destabilizes representations and induces…

Computation and Language · Computer Science 2026-05-15 Qingyuan Liu , Jia-Chen Gu , Yunzhi Yao , Hong Wang , Nanyun Peng