English
Related papers

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

200 papers

This paper proposes a novel formulation for reinforcement learning (RL) with large language models, explaining why and under what conditions the true sequence-level reward can be optimized via a surrogate token-level objective in policy…

Machine Learning · Computer Science 2025-12-04 Chujie Zheng , Kai Dang , Bowen Yu , Mingze Li , Huiqiang Jiang , Junrong Lin , Yuqiong Liu , Hao Lin , Chencan Wu , Feng Hu , An Yang , Jingren Zhou , Junyang Lin

Contemporary machine learning models, including large language models, exhibit remarkable capabilities in static tasks yet falter in non-stationary environments due to rigid architectures that hinder continual adaptation and lifelong…

Machine Learning · Computer Science 2026-05-15 Akbar Anbar Jafari , Cagri Ozcinar , Gholamreza Anbarjafari

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

Large language models (LLMs) demonstrate remarkable reasoning capabilities, yet their performance often deteriorates sharply in long-horizon tasks, exhibiting systematic breakdown beyond certain scales. Conventional explanations primarily…

Artificial Intelligence · Computer Science 2026-02-09 Hsien-Jyh Liao

Training stability is typically regarded as a prerequisite for reliable optimization in large language models. In this work, we analyze how stabilizing training dynamics affects the induced generation distribution. We show that under…

Artificial Intelligence · Computer Science 2026-02-10 Xianzhe Meng , Qiangsheng Zeng , Ling Luo , Qinghan Yang , Jiarui Hao , Wenbo Wu , Qinyu Wang , Rui Yin , Lin Qi , Renzhi Lu

Large language models are strong sequence predictors, yet standard inference relies on immutable context histories. After making an error at generation step t, the model lacks an updatable memory mechanism that improves predictions for step…

Computation and Language · Computer Science 2026-01-21 Yuxing Lu , J. Ben Tamo , Weichen Zhao , Nan Sun , Yishan Zhong , Wenqi Shi , Jinzhuo Wang , May D. Wang

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…

Large Language Models (LLMs) are increasingly deployed for structured data generation, yet output consistency remains critical for production applications. We introduce a comprehensive framework for evaluating and improving consistency in…

Computation and Language · Computer Science 2026-01-01 Guanghui Wang , Jinze Yu , Xing Zhang , Dayuan Jiang , Yin Song , Tomal Deb , Xuefeng Liu , Peiyang He

In this work, we show that Latent Flow-Matching (LFM) models are robust to different types of perturbations, including data reduction and model capacity shrinkage. We characterize this stability by their tendency to generate similar outputs…

Machine Learning · Computer Science 2026-05-12 Rania Briq , Michael Kamp , Ohad Fried , Sarel Cohen , Stefan Kesselheim

We introduce Flashback Learning (FL), a novel method designed to harmonize the stability and plasticity of models in Continual Learning (CL). Unlike prior approaches that primarily focus on regularizing model updates to preserve old…

Machine Learning · Computer Science 2025-06-03 Leila Mahmoodi , Peyman Moghadam , Munawar Hayat , Christian Simon , Mehrtash Harandi

We develop a finite-dimensional sensitivity framework for studying stability in learning systems whose states include representations, parameters, and update variables. The central object is the \emph{Learning Stability Profile}, a…

Machine Learning · Computer Science 2026-05-26 Ronald Katende

Supervised fine-tuning (SFT) of large language models can be viewed as an off-policy learning problem, where expert demonstrations come from a fixed behavior policy while training aims to optimize a target policy. Importance sampling is the…

Machine Learning · Computer Science 2025-09-22 Shiwan Zhao , Xuyang Zhao , Jiaming Zhou , Aobo Kong , Qicheng Li , Yong Qin

Large Language Models (LLMs) are typically static after training, yet real-world applications require continual adaptation to new knowledge without degrading existing capabilities. Standard approaches to updating models, like full…

Machine Learning · Computer Science 2026-04-08 Satyam Goyal , Anirudh Kanchi , Garv Shah , Prakhar Gupta

Knowledge editing (KE) enables precise modifications to factual content in large language models (LLMs). Existing KE methods are largely designed for dense architectures, limiting their applicability to the increasingly prevalent sparse…

Machine Learning · Computer Science 2026-02-12 Yupu Gu , Rongzhe Wei , Andy Zhu , Pan Li

The vast number of parameters in large language models (LLMs) endows them with remarkable capabilities, allowing them to excel in a variety of natural language processing tasks. However, this complexity also presents challenges, making LLMs…

Computation and Language · Computer Science 2023-10-24 Mingzhe Du , Anh Tuan Luu , Bin Ji , See-kiong Ng

Motivation: A perennial challenge for biomedical researchers and clinical practitioners is to stay abreast with the rapid growth of publications and medical notes. Natural language processing (NLP) has emerged as a promising direction for…

Computation and Language · Computer Science 2021-12-16 Robert Tinn , Hao Cheng , Yu Gu , Naoto Usuyama , Xiaodong Liu , Tristan Naumann , Jianfeng Gao , Hoifung Poon

The widespread dissemination of fake news on social media has significantly impacted society, resulting in serious consequences. Conventional deep learning methodologies employing small language models (SLMs) suffer from extensive…

Computation and Language · Computer Science 2025-06-06 Ziyi Zhou , Xiaoming Zhang , Litian Zhang , Yibo Zhang , Zhenyu Guan , Chaozhuo Li , Philip S. Yu

Fine-tuning, a foundational method for adapting large language models, has long been considered ineffective for model editing. Here, we challenge this belief, arguing that the reported failure arises not from the inherent limitation of…

Computation and Language · Computer Science 2026-02-27 Wanli Yang , Rui Tang , Hongyu Zang , Du Su , Qi Cao , Jingang Wang , Huawei Shen , Xueqi Cheng , Fei Sun

Large language models (LLMs) exhibit exceptional performance across various domains, yet they face critical safety concerns. Model editing has emerged as an effective approach to mitigate these issues. Existing model editing methods often…

Computation and Language · Computer Science 2026-01-19 Xiaojie Gu , Guangxu Chen , Yuheng Yang , Jingxin Han , Andi Zhang

Synthetic data has been increasingly used to train frontier generative models. However, recent studies raise key concerns that iteratively retraining a generative model on its self-generated synthetic data may keep deteriorating model…

Machine Learning · Statistics 2026-03-09 Bingji Yi , Qiyuan Liu , Yuwei Cheng , Haifeng Xu