English
Related papers

Related papers: More Edits, More Stable: Understanding the Lifelon…

200 papers

Model averaging has received much attention in the past two decades, which integrates available information by averaging over potential models. Although various model averaging methods have been developed, there are few literatures on the…

Machine Learning · Statistics 2023-11-27 Hengkun Zhu , Guohua Zou

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…

Computation and Language · Computer Science 2025-06-13 Wei Sun , Tingyu Qu , Mingxiao Li , Jesse Davis , Marie-Francine Moens

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

To date, the instability of prognostic predictors in a sparse high dimensional model, which hinders their clinical adoption, has received little attention. Stable prediction is often overlooked in favour of performance. Yet, stability…

Machine Learning · Statistics 2016-09-29 Shivapratap Gopakumar , Truyen Tran , Dinh Phung , Svetha Venkatesh

Large Language Models (LLMs) excel at long-context understanding but exhibit significant limitations in long-form generation. Existing studies primarily focus on single-generation quality, generally overlooking the volatility of the output.…

Computation and Language · Computer Science 2026-05-05 Zhitao He , Haolin Yang , Rui Min , Zeyu Qin , Yi R. Fung

Generating stylized large language model (LLM) responses via representation editing is a promising way for fine-grained output control. However, there exists an inherent trade-off: imposing a distinctive style often degrades truthfulness.…

Computation and Language · Computer Science 2025-08-08 Chenglei Shen , Zhongxiang Sun , Teng Shi , Xiao Zhang , Jun Xu

Many industrial machine learning (ML) systems require frequent retraining to keep up-to-date with constantly changing data. This retraining exacerbates a large challenge facing ML systems today: model training is unstable, i.e., small…

Computation and Language · Computer Science 2020-03-12 Megan Leszczynski , Avner May , Jian Zhang , Sen Wu , Christopher R. Aberger , Christopher Ré

Lifelong learning (LL) aims to continuously acquire new knowledge while retaining previously learned knowledge. A central challenge in LL is the stability-plasticity dilemma, which requires models to balance the preservation of previous…

Machine Learning · Computer Science 2025-03-11 Ruiyu Wang , Sen Wang , Xinxin Zuo , Qiang Sun

Large language models (LLMs) have achieved remarkable performance on various natural language tasks. However, they are trained on static corpora and their knowledge can become outdated quickly in the fast-changing world. This motivates the…

Computation and Language · Computer Science 2025-03-04 Tianci Liu , Ruirui Li , Yunzhe Qi , Hui Liu , Xianfeng Tang , Tianqi Zheng , Qingyu Yin , Monica Xiao Cheng , Jun Huan , Haoyu Wang , Jing Gao

Null-space-based methods have garnered considerable attention in model editing by constraining updates to the null space of the pre-existing knowledge representation, thereby preserving the model's original behavior. However, in practice…

Computation and Language · Computer Science 2026-05-12 Bingqing Liu , Wei Liu , Yuhua Li

Sequential knowledge editing techniques aim to continuously update knowledge in large language models at low cost, preventing models from generating outdated or incorrect information. However, existing sequential editing methods suffer from…

Computation and Language · Computer Science 2026-04-01 Ding Cao , Yuchen Cai , Yuqing Huang , Xuesong He , Rongxi Guo , Guiquan Liu , Guangzhong Sun

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

Model editing aims to correct errors in large, pretrained models without altering unrelated behaviors. While some recent works have edited vision-language models (VLMs), no existing editors tackle reasoning-heavy tasks, which typically…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Jiaxing Qiu , Kaihua Hou , Roxana Daneshjou , Ahmed Alaa , Thomas Hartvigsen

As Large Language Models (LLMs) expand in capability and application scope, their trustworthiness becomes critical. A vital risk is intrinsic deception, wherein models strategically mislead users to achieve their own objectives. Existing…

Machine Learning · Computer Science 2026-03-31 Guoxi Zhang , Jiawei Chen , Tianzhuo Yang , Lang Qin , Juntao Dai , Yaodong Yang , Jingwei Yi

Aligning large language models (LLMs) with human objectives is crucial for real-world applications. However, fine-tuning LLMs for alignment often suffers from unstable training and requires substantial computing resources. Test-time…

Artificial Intelligence · Computer Science 2024-11-05 Lingkai Kong , Haorui Wang , Wenhao Mu , Yuanqi Du , Yuchen Zhuang , Yifei Zhou , Yue Song , Rongzhi Zhang , Kai Wang , Chao Zhang

Although Large Language Models (LLMs) achieve strong alignment through supervised fine-tuning and reinforcement learning from human feedback, the alignment is often fragile under subsequent fine-tuning. Existing explanations either…

Machine Learning · Computer Science 2026-05-19 Yuhan Huang , Huanran Chen , Yinpeng Dong

Finding appropriate prompts for the specific task has become an important issue as the usage of Large Language Models (LLM) has expanded. Reinforcement Learning (RL) is widely used for prompt tuning, but its inherent instability and…

Computation and Language · Computer Science 2024-10-11 Minchan Kwon , Gaeun Kim , Jongsuk Kim , Haeil Lee , Junmo Kim

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

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

Machine unlearning aims to remove the influence of specific training data from pre-trained models without retraining from scratch, and is increasingly important for large language models (LLMs) due to safety, privacy, and legal concerns.…

Computation and Language · Computer Science 2026-03-17 Ruihao Pan , Suhang Wang
‹ Prev 1 3 4 5 6 7 10 Next ›