English
Related papers

Related papers: Spectral Characterization and Mitigation of Sequen…

200 papers

Restoration of images contaminated by different adverse weather conditions such as fog, snow, and rain is a challenging task due to the varying nature of the weather conditions. Most of the existing methods focus on any one particular…

Computer Vision and Pattern Recognition · Computer Science 2025-07-28 Kotha Kartheek , Lingamaneni Gnanesh Chowdary , Snehasis Mukherjee

The widespread use of diffusion models has led to an abundance of AI-generated data, raising concerns about model collapse -- a phenomenon in which recursive iterations of training on synthetic data lead to performance degradation. Prior…

Machine Learning · Computer Science 2025-12-29 Lianghe Shi , Meng Wu , Huijie Zhang , Zekai Zhang , Molei Tao , Qing Qu

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

Supervised Fine-Tuning (SFT) is a critical step for enhancing the instruction-following capabilities of Large Language Models (LLMs) and adapting them to specialized domains. However, SFT often leads to a degradation of the model's general…

Computation and Language · Computer Science 2025-07-01 Fei Ding , Baiqiao Wang

The imperative task of revising or updating the knowledge stored within large language models arises from two distinct sources: intrinsic errors inherent in the model which should be corrected and outdated knowledge due to external shifts…

Computation and Language · Computer Science 2023-12-15 Xunjian Yin , Jin Jiang , Liming Yang , Xiaojun Wan

Explicit reasoning models are trained to produce intermediate reasoning traces before final answers, but downstream fine-tuning is often performed on ordinary instruction-response data that contains no such traces. We show that this…

Machine Learning · Computer Science 2026-05-21 Lukas Twist , Helen Yannakoudakis , Jie M. Zhang

As the world changes, we need to be able to update our models and correct false information without costly retraining. Knowledge-based model editing enables precise modifications to the weights of large language models in order to modify…

Machine Learning · Computer Science 2025-02-28 Elan Markowitz , Anil Ramakrishna , Ninareh Mehrabi , Charith Peris , Rahul Gupta , Kai-Wei Chang , Aram Galstyan

In the era of proliferation of large language and image generation models, the phenomenon of "model collapse" refers to the situation whereby as a model is trained recursively on data generated from previous generations of itself over time,…

Machine Learning · Computer Science 2024-05-02 Elvis Dohmatob , Yunzhen Feng , Julia Kempe

While most continual learning methods focus on mitigating forgetting and improving accuracy, they often overlook the critical aspect of network calibration, despite its importance. Neural collapse, a phenomenon where last-layer features…

Machine Learning · Computer Science 2026-04-23 Trung-Anh Dang , Vincent Nguyen , Ngoc-Son Vu , Christel Vrain

Model editing aims to efficiently alter the behavior of Large Language Models (LLMs) within a desired scope, while ensuring no adverse impact on other inputs. Recent years have witnessed various model editing methods been proposed. However,…

Computation and Language · Computer Science 2024-06-04 Renzhi Wang , Piji Li

Large language models (LLMs) acquire substantial world knowledge during pre-training, which is further shaped by post-training techniques such as supervised fine-tuning (SFT). However, the impact of SFT on a model's knowledge remains…

Computation and Language · Computer Science 2026-02-11 Junjie Ye , Yuming Yang , Yang Nan , Shuo Li , Qi Zhang , Tao Gui , Xuanjing Huang , Peng Wang , Zhongchao Shi , Jianping Fan

Current knowledge editing methods for large language models (LLMs) struggle to maintain logical consistency when propagating ripple effects to associated facts. We propose ChainEdit, a framework that synergizes knowledge graph-derived…

Computation and Language · Computer Science 2025-07-14 Zilu Dong , Xiangqing Shen , Zinong Yang , Rui Xia

Speculative decoding (SD) has emerged as an effective technique to accelerate large language model (LLM) inference without compromising output quality. However, the achievable speedup largely depends on the effectiveness of the drafting…

Computation and Language · Computer Science 2025-11-04 Min Fang , Zhihui Fu , Qibin Zhao , Jun Wang

Within the scaling laws paradigm, which underpins the training of large neural networks like ChatGPT and Llama, we consider a supervised regression setting and establish the existance of a strong form of the model collapse phenomenon, a…

Machine Learning · Computer Science 2024-10-10 Elvis Dohmatob , Yunzhen Feng , Arjun Subramonian , Julia Kempe

Large language models (LLMs) often suffer from catastrophic forgetting in continual learning: after learning new tasks sequentially, they perform worse on earlier tasks. Existing methods mitigate catastrophic forgetting by data replay,…

Machine Learning · Computer Science 2026-05-08 Yazheng Liu , Yuxuan Wan , Rui Xu , Xi Zhang , Sihong Xie , Hui Xiong

Advances in variational inference enable parameterisation of probabilistic models by deep neural networks. This combines the statistical transparency of the probabilistic modelling framework with the representational power of deep learning.…

Computation and Language · Computer Science 2020-05-05 Tom Pelsmaeker , Wilker Aziz

Deep neural networks achieve impressive performance but remain difficult to interpret and control. We present SALVE (Sparse Autoencoder-Latent Vector Editing), a unified "discover, validate, and control" framework that bridges mechanistic…

Machine Learning · Computer Science 2026-03-10 Vegard Flovik

We investigate why deep neural networks suffer from loss of plasticity in deep continual learning, failing to learn new tasks without reinitializing parameters. We show that this failure is preceded by Hessian spectral collapse at new-task…

Machine Learning · Computer Science 2025-09-30 Naicheng He , Kaicheng Guo , Arjun Prakash , Saket Tiwari , Ruo Yu Tao , Tyrone Serapio , Amy Greenwald , George Konidaris

Catastrophic forgetting remains a central challenge in continual learning, where models are required to integrate new knowledge over time without losing what they have previously learned. In prior work, we introduced Cobweb/4V, a…

Machine Learning · Computer Science 2025-10-29 Nicki Barari , Edward Kim , Christopher MacLellan

Large Language Models (LLMs) have shown proficiency in question-answering tasks but often struggle to integrate real-time knowledge, leading to potentially outdated or inaccurate responses. This problem becomes even more challenging when…

Computation and Language · Computer Science 2024-08-15 Yucheng Shi , Qiaoyu Tan , Xuansheng Wu , Shaochen Zhong , Kaixiong Zhou , Ninghao Liu