English
Related papers

Related papers: Improving Length-Generalization in Transformers vi…

200 papers

The evolving sophistication and intricacies of Large Language Models (LLMs) yield unprecedented advancements, yet they simultaneously demand considerable computational resources and incur significant costs. To alleviate these challenges,…

Computation and Language · Computer Science 2023-10-03 Hongye Jin , Xiaotian Han , Jingfeng Yang , Zhimeng Jiang , Chia-Yuan Chang , Xia Hu

Multi-task learning can leverage information learned by one task to benefit the training of other tasks. Despite this capacity, naively training all tasks together in one model often degrades performance, and exhaustively searching through…

Machine Learning · Computer Science 2021-10-27 Christopher Fifty , Ehsan Amid , Zhe Zhao , Tianhe Yu , Rohan Anil , Chelsea Finn

This paper explores the impact of extending input lengths on the capabilities of Large Language Models (LLMs). Despite LLMs advancements in recent times, their performance consistency across different input lengths is not well understood.…

Computation and Language · Computer Science 2024-07-11 Mosh Levy , Alon Jacoby , Yoav Goldberg

Chain of Thought (CoT) prompting has been shown to significantly improve the performance of large language models (LLMs), particularly in arithmetic and reasoning tasks, by instructing the model to produce intermediate reasoning steps.…

Machine Learning · Computer Science 2025-03-03 Jianhao Huang , Zixuan Wang , Jason D. Lee

Length generalization, the ability to solve problems of longer sequences than those observed during training, poses a core challenge of Transformer-based large language models (LLM). Although existing studies have predominantly focused on…

Computation and Language · Computer Science 2026-01-29 Zhouqi Hua , Wenwei Zhang , Chengqi Lyu , Yuzhe Gu , Songyang Gao , Kuikun Liu , Dahua Lin , Kai Chen

State-of-the-art pretrained language models tend to perform below their capabilities when applied out-of-the-box on tasks that require understanding and working with numbers. Recent work suggests two main reasons for this: (1) popular…

Computation and Language · Computer Science 2023-06-12 Dominic Petrak , Nafise Sadat Moosavi , Iryna Gurevych

Transformers struggle with length generalisation, displaying poor performance even on basic tasks. We test whether these limitations can be explained through two key failures of the self-attention mechanism. The first is the inability to…

Machine Learning · Computer Science 2025-10-07 Mattia Opper , Roland Fernandez , Paul Smolensky , Jianfeng Gao

Transformer-based masked language models such as BERT, trained on general corpora, have shown impressive performance on downstream tasks. It has also been demonstrated that the downstream task performance of such models can be improved by…

Computation and Language · Computer Science 2023-05-04 Zhi Hong , Aswathy Ajith , Gregory Pauloski , Eamon Duede , Kyle Chard , Ian Foster

Despite the recent advances showing that a model pre-trained on large-scale source code data is able to gain appreciable generalization capability, it still requires a sizeable amount of data on the target task for fine-tuning. And the…

Software Engineering · Computer Science 2023-02-13 Changan Niu , Chuanyi Li , Vincent Ng , Bin Luo

Transfer learning is a useful technique for achieving improved performance and reducing training costs by leveraging the knowledge gained from source tasks and applying it to target tasks. Assessing the effectiveness of transfer learning…

Machine Learning · Computer Science 2023-06-12 Peizhong Ju , Sen Lin , Mark S. Squillante , Yingbin Liang , Ness B. Shroff

In-context learning enables transformer models to generalize to new tasks based solely on input prompts, without any need for weight updates. However, existing training paradigms typically rely on large, unstructured datasets that are…

Multi-task learning and self-training are two common ways to improve a machine learning model's performance in settings with limited training data. Drawing heavily on ideas from those two approaches, we suggest transductive auxiliary task…

Computation and Language · Computer Science 2019-09-24 Johannes Bjerva , Katharina Kann , Isabelle Augenstein

In many real-world scenarios, data to train machine learning models becomes available over time. Unfortunately, these models struggle to continually learn new concepts without forgetting what has been learnt in the past. This phenomenon is…

Computation and Language · Computer Science 2023-01-16 Beyza Ermis , Giovanni Zappella , Martin Wistuba , Aditya Rawal , Cedric Archambeau

In large language model training, input documents are typically concatenated together and then split into sequences of equal length to avoid padding tokens. Despite its efficiency, the concatenation approach compromises data integrity -- it…

Computation and Language · Computer Science 2024-05-03 Hantian Ding , Zijian Wang , Giovanni Paolini , Varun Kumar , Anoop Deoras , Dan Roth , Stefano Soatto

When language models (LMs) are trained to forget (or "unlearn'') a skill, how precisely does their behavior change? We study the behavior of transformer LMs in which tasks have been forgotten via fine-tuning on randomized labels. Such LMs…

Machine Learning · Computer Science 2024-09-05 Eric Zhang , Leshem Chosen , Jacob Andreas

The impressive capabilities of large language models (LLMs) have sparked debate over whether these models genuinely generalize to unseen tasks or predominantly rely on memorizing vast amounts of pretraining data. To explore this issue, we…

Computation and Language · Computer Science 2025-03-04 Xinyi Wang , Antonis Antoniades , Yanai Elazar , Alfonso Amayuelas , Alon Albalak , Kexun Zhang , William Yang Wang

Despite the remarkable capabilities of modern large language models (LLMs), the mechanisms behind their problem-solving abilities remain elusive. In this work, we aim to better understand how the learning dynamics of LLM finetuning shapes…

Machine Learning · Computer Science 2024-11-19 Katie Kang , Amrith Setlur , Dibya Ghosh , Jacob Steinhardt , Claire Tomlin , Sergey Levine , Aviral Kumar

While robot learning has demonstrated promising results for enabling robots to automatically acquire new skills, a critical challenge in deploying learning-based systems is scale: acquiring enough data for the robot to effectively…

Instruction tuning of language models has demonstrated the ability to enhance model generalization to unseen tasks via in-context learning using a few examples. However, typical supervised learning still requires a plethora of downstream…

Computation and Language · Computer Science 2023-06-12 Himanshu Gupta , Saurabh Arjun Sawant , Swaroop Mishra , Mutsumi Nakamura , Arindam Mitra , Santosh Mashetty , Chitta Baral

Training large transformer models from scratch for a target task requires lots of data and is computationally demanding. The usual practice of transfer learning overcomes this challenge by initializing the model with weights of a pretrained…