English
Related papers

Related papers: Operationalising the Superficial Alignment Hypothe…

200 papers

We present Junk DNA Hypothesis by adopting a novel task-centric angle for the pre-trained weights of large language models (LLMs). It has been believed that weights in LLMs contain significant redundancy, leading to the conception that a…

Machine Learning · Computer Science 2026-05-01 Lu Yin , Ajay Jaiswal , Shiwei Liu , Souvik Kundu , Zhangyang Wang

This paper addresses the limited transfer and adaptation capabilities of large language models in low-resource language scenarios. It proposes a unified framework that combines a knowledge transfer module with parameter-efficient…

Computation and Language · Computer Science 2025-07-03 Shuangquan Lyu , Yingnan Deng , Guiran Liu , Zhen Qi , Ruotong Wang

Large language models (LLMs), typically designed as a function of next-word prediction, have excelled across extensive NLP tasks. Despite the generality, next-word prediction is often not an efficient formulation for many of the tasks,…

Computation and Language · Computer Science 2023-11-03 Yuheng Zha , Yichi Yang , Ruichen Li , Zhiting Hu

LLMs' performance on complex tasks is still unsatisfactory. A key issue is that presently LLMs learn in a data-driven schema, while the instructions about these complex tasks are both scarce and hard to collect or construct. On the…

Machine Learning · Computer Science 2024-10-21 Yang Zhao , Li Du , Xiao Ding , Kai Xiong , Ting Liu , Bing Qin

Learning and the ability to learn are important factors in development and evolutionary processes [1]. Depending on the level, the complexity of learning can strongly vary. While associative learning can explain simple learning behaviour…

Neurons and Cognition · Quantitative Biology 2007-05-23 Reimer Kuehn , Ion-Olimpiu Stamatescu

Despite rapid advances in the capabilities of Large Language Models (LLMs), they continue to struggle with following relatively simple and unambiguous instructions, particularly when compositional structure is involved. Recent work suggests…

Computation and Language · Computer Science 2026-03-12 Prince Kumar , Rudra Murthy , Riyaz Bhat , Danish Contractor

Finetuning a pretrained model has become a standard approach for training neural networks on novel tasks, resulting in fast convergence and improved performance. In this work, we study an alternative finetuning method, where instead of…

Machine Learning · Computer Science 2023-07-04 Gal Kaplun , Andrey Gurevich , Tal Swisa , Mazor David , Shai Shalev-Shwartz , Eran Malach

The goal of continual learning is to improve the performance of recognition models in learning sequentially arrived data. Although most existing works are established on the premise of learning from scratch, growing efforts have been…

Computer Vision and Pattern Recognition · Computer Science 2023-10-10 Gengwei Zhang , Liyuan Wang , Guoliang Kang , Ling Chen , Yunchao Wei

Most classification models work by first predicting a posterior probability distribution over all classes and then selecting that class with the largest estimated probability. In many settings however, the quality of posterior probability…

Computation and Language · Computer Science 2020-05-04 Taehee Jung , Dongyeop Kang , Hua Cheng , Lucas Mentch , Thomas Schaaf

We have witnessed superhuman intelligence thanks to the fast development of large language models and multimodal language models. As the application of such superhuman models becomes more and more popular, a critical question arises here:…

Computation and Language · Computer Science 2024-12-24 Minlie Huang , Yingkang Wang , Shiyao Cui , Pei Ke , Jie Tang

Multi-task learning is a framework that enforces different learning tasks to share their knowledge to improve their generalization performance. It is a hot and active domain that strives to handle several core issues; particularly, which…

Machine Learning · Computer Science 2021-02-23 Johnny Torres , Guangji Bai , Junxiang Wang , Liang Zhao , Carmen Vaca , Cristina Abad

Continual learning aims to learn a series of tasks sequentially without forgetting the knowledge acquired from the previous ones. In this work, we propose the Hessian Aware Low-Rank Perturbation algorithm for continual learning. By modeling…

We study the problem of minimizing the average of a very large number of smooth functions, which is of key importance in training supervised learning models. One of the most celebrated methods in this context is the SAGA algorithm. Despite…

Machine Learning · Computer Science 2019-01-28 Xu Qian , Zheng Qu , Peter Richtárik

Parameter regularization or allocation methods are effective in overcoming catastrophic forgetting in lifelong learning. However, they solve all tasks in a sequence uniformly and ignore the differences in the learning difficulty of…

Machine Learning · Computer Science 2023-04-12 Wenjin Wang , Yunqing Hu , Qianglong Chen , Yin Zhang

This paper presents a novel information-theoretic perspective on generalization in machine learning by framing the learning problem within the context of lossy compression and applying finite blocklength analysis. In our approach, the…

Machine Learning · Computer Science 2026-02-05 Kosuke Sugiyama , Masato Uchida

Standard deep learning relies on Backpropagation (BP), which is constrained by biologically implausible weight symmetry and suffers from significant gradient interference within dense representations. To mitigate these bottlenecks, we…

Machine Learning · Computer Science 2026-01-30 Fanping Liu , Hua Yang , Jiasi Zou

In this work, we investigate whether small language models can determine high-quality subsets of large-scale text datasets that improve the performance of larger language models. While existing work has shown that pruning based on the…

Machine Learning · Computer Science 2024-06-03 Zachary Ankner , Cody Blakeney , Kartik Sreenivasan , Max Marion , Matthew L. Leavitt , Mansheej Paul

Probably Approximately Correct (i.e., PAC) learning is a core concept of sample complexity theory, and efficient PAC learnability is often seen as a natural counterpart to the class P in classical computational complexity. But while the…

Computational Complexity · Computer Science 2023-04-28 Cornelius Brand , Robert Ganian , Kirill Simonov

Trained models are often composed with post-hoc transforms such as temperature scaling (TS), ensembling and stochastic weight averaging (SWA) to improve performance, robustness, uncertainty estimation, etc. However, such transforms are…

Machine Learning · Computer Science 2024-10-07 Rishabh Ranjan , Saurabh Garg , Mrigank Raman , Carlos Guestrin , Zachary Lipton

Learning representations of well-trained neural network models holds the promise to provide an understanding of the inner workings of those models. However, previous work has either faced limitations when processing larger networks or was…

Machine Learning · Computer Science 2024-06-17 Konstantin Schürholt , Michael W. Mahoney , Damian Borth