English
Related papers

Related papers: Understanding Domain Learning in Language Models T…

200 papers

In the problem of domain transfer learning, we learn a model for the predic-tion in a target domain from the data of both some source domains and the target domain, where the target domain is in lack of labels while the source domain has…

Computer Vision and Pattern Recognition · Computer Science 2018-05-21 Guohui Zhang , Gaoyuan Liang , Fang Su , Fanxin Qu , Jing-Yan Wang

We study whether Large Language Models (LLMs) inherently capture domain-specific nuances in natural language. Our experiments probe the domain sensitivity of LLMs by examining their ability to distinguish queries from different domains…

Recent advances in NLP are brought by a range of large-scale pretrained language models (PLMs). These PLMs have brought significant performance gains for a range of NLP tasks, circumventing the need to customize complex designs for specific…

Computation and Language · Computer Science 2022-11-08 Xu Guo , Han Yu

Deep convolutional neural networks (CNNs) have been shown to be very successful in a wide range of image processing applications. However, due to their increasing number of model parameters and an increasing availability of large amounts of…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Axel Klawonn , Martin Lanser , Janine Weber

Continued pre-training of small language models offers a promising path for domain adaptation with limited computational resources. I've investigated this approach within educational domains, evaluating it as a resource-efficient…

Computation and Language · Computer Science 2025-04-15 Salman Faroz

Pre-trained word embeddings are the primary method for transfer learning in several Natural Language Processing (NLP) tasks. Recent works have focused on using unsupervised techniques such as language modeling to obtain these embeddings. In…

Computation and Language · Computer Science 2019-07-01 Mihir Kale , Aditya Siddhant , Sreyashi Nag , Radhika Parik , Matthias Grabmair , Anthony Tomasic

Large, general purpose language models have demonstrated impressive performance across many different conversational domains. While multi-domain language models achieve low overall perplexity, their outputs are not guaranteed to stay within…

Computation and Language · Computer Science 2023-12-11 Anmol Kabra , Ethan R. Elenberg

Existing techniques to adapt semantic segmentation networks across the source and target domains within deep convolutional neural networks (CNNs) deal with all the samples from the two domains in a global or category-aware manner. They do…

Computer Vision and Pattern Recognition · Computer Science 2020-12-18 Minsu Kim , Sunghun Joung , Seungryong Kim , JungIn Park , Ig-Jae Kim , Kwanghoon Sohn

We propose a new technique, Singular Vector Canonical Correlation Analysis (SVCCA), a tool for quickly comparing two representations in a way that is both invariant to affine transform (allowing comparison between different layers and…

Machine Learning · Statistics 2017-11-09 Maithra Raghu , Justin Gilmer , Jason Yosinski , Jascha Sohl-Dickstein

We study the task of unsupervised domain adaptation, where no labeled data from the target domain is provided during training time. To deal with the potential discrepancy between the source and target distributions, both in features and…

Machine Learning · Computer Science 2017-10-03 Cuong D. Tran , Ognjen Rudovic , Vladimir Pavlovic

Inspired by the inductive transfer learning on computer vision, many efforts have been made to train contextualized language models that boost the performance of natural language processing tasks. These models are mostly trained on large…

Computation and Language · Computer Science 2021-02-12 Shohreh Shaghaghian , Luna , Feng , Borna Jafarpour , Nicolai Pogrebnyakov

Deep learning models have achieved great success on various vision challenges, but a well-trained model would face drastic performance degradation when applied to unseen data. Since the model is sensitive to domain shift, unsupervised…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Ziyu Ye , Chen Ju , Chaofan Ma , Xiaoyun Zhang

Multilingual language models (MLLMs) have demonstrated remarkable abilities to transfer knowledge across languages, despite being trained without explicit cross-lingual supervision. We analyze the parameter spaces of three MLLMs to study…

Computation and Language · Computer Science 2025-06-03 Frederick Riemenschneider , Anette Frank

Although there is significant progress in supervised semantic segmentation, it remains challenging to deploy the segmentation models to unseen domains due to domain biases. Domain adaptation can help in this regard by transferring knowledge…

Computer Vision and Pattern Recognition · Computer Science 2022-05-03 Binhui Xie , Mingjia Li , Shuang Li

Multi-domain translation seeks to learn a probabilistic coupling between marginal distributions that reflects the correspondence between different domains. We assume that data from different domains are generated from a shared latent…

Machine Learning · Computer Science 2019-02-12 Karren D. Yang , Caroline Uhler

Continuously-growing data volumes lead to larger generic models. Specific use-cases are usually left out, since generic models tend to perform poorly in domain-specific cases. Our work addresses this gap with a method for selecting…

Computation and Language · Computer Science 2022-02-08 Javad Pourmostafa Roshan Sharami , Dimitar Shterionov , Pieter Spronck

Domain adaptation seeks to leverage the abundant label information in a source domain to improve classification performance in a target domain with limited labels. While the field has seen extensive methodological development, its…

Machine Learning · Statistics 2025-07-31 Elif Vural , Huseyin Karaca

Learning high-quality domain word embeddings is important for achieving good performance in many NLP tasks. General-purpose embeddings trained on large-scale corpora are often sub-optimal for domain-specific applications. However,…

Computation and Language · Computer Science 2018-05-28 Hu Xu , Bing Liu , Lei Shu , Philip S. Yu

Pre-trained language models (PLMs) that use subword tokenization schemes can succeed at a variety of language tasks that require character-level information, despite lacking explicit access to the character composition of tokens. Here,…

Computation and Language · Computer Science 2022-06-07 Ayush Kaushal , Kyle Mahowald

Many NLP applications, such as biomedical data and technical support, have 10-100 million tokens of in-domain data and limited computational resources for learning from it. How should we train a language model in this scenario? Most…

Computation and Language · Computer Science 2020-10-01 Charles Welch , Rada Mihalcea , Jonathan K. Kummerfeld