paper-with-me

홈 › Papers

Adapting a Language Model While Preserving its General Knowledge

2023-01-21 · Zixuan Ke, Yijia Shao, Haowei Lin, Hu Xu, Lei Shu, Bing Liu

Domain-adaptive pre-training (or DA-training for short), also known as post-training, aims to train a pre-trained general-purpose language model (LM) using an unlabeled corpus of a particular domain to adapt the LM so that end-tasks in the domain can give improved performances. However, existing DA-training methods are in some sense blind as they do not explicitly identify what knowledge in the LM should be preserved and what should be changed by the domain corpus. This paper shows that the existing methods are suboptimal and proposes a novel method to perform a more informed adaptation of the knowledge in the LM by (1) soft-masking the attention heads based on their importance to best preserve the general knowledge in the LM and (2) contrasting the representations of the general and the full (both general and domain knowledge) to learn an integrated representation with both general and domain-specific knowledge. Experimental results will demonstrate the effectiveness of the proposed approach.

📄 PDF Abstract BibTeX arXiv:2301.08986

Code (2)

uic-liu-lab/dga 공식 구현 pytorch
UIC-Liu-Lab/ContinualLM pytorch

Tasks

Continual LearningGeneral KnowledgeLanguage ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

Adapting Vision-Language Model with Fine-grained Semantics for Open-Vocabulary Segmentation

2024-09-24 · Yong Xien Chng, Xuchong Qiu, Yizeng Han, Kai Ding 외

Despite extensive research, open-vocabulary segmentation methods still struggle to generalize across diverse domains. To reduce the computational cost of adapting Vision-Language Models (VLMs) while preserving their pre-…

Language ModelingLanguage ModellingOpen Vocabulary Panoptic SegmentationPanoptic Segmentation

Adapting Vision-Language Models for E-commerce Understanding at Scale

2026-02-12 · Matteo Nulli, Vladimir Orshulevich, Tala Bazazo, Christian Herold 외 arxiv

E-commerce product understanding demands by nature, strong multimodal comprehension from text, images, and structured attributes. General-purpose Vision-Language Models (VLMs) enable generalizable multimodal latent model…

Instruction FollowingAttribute Extraction

EvoPrompt: Guided Prompt Evolution for Vision-Language Models Adaptation

2026-03-10 · Enming Zhang, Jiayang Li, Yanlong Wang, Yanru Wu 외 arxiv

The adaptation of large-scale vision-language models (VLMs) to downstream tasks with limited labeled data remains a significant challenge. While parameter-efficient prompt learning methods offer a promising path, they of…

Few-Shot Learning

Select and Distill: Selective Dual-Teacher Knowledge Transfer for Continual Learning on Vision-Language Models

2024-03-14 · Yu-Chu Yu, Chi-Pin Huang, Jr-Jen Chen, Kai-Po Chang 외

Large-scale vision-language models (VLMs) have shown a strong zero-shot generalization capability on unseen-domain data. However, adapting pre-trained VLMs to a sequence of downstream tasks often leads to the forgetting …

Continual LearningKnowledge DistillationTransfer Learningzero-shot-classification+2

Modular Multi-Task Learning for Chemical Reaction Prediction

2026-02-11 · Jiayun Pang, Ahmed M. Zaitoun, Xacobe Couso Cambeiro, Ivan Vulić arxiv

Adapting large language models (LLMs) trained on broad organic chemistry to smaller, domain-specific reaction datasets is a key challenge in chemical and pharmaceutical R&D. Effective specialisation requires learning new…

parameter-efficient fine-tuningChemical Reaction PredictionForward reaction predictionMulti-Task Learning