Can I read DALLMi: Domain Adaption for LLM-based Multi-label Classifier on EtoBox?

DALLMi: Domain Adaption for LLM-based Multi-label Classifier by Beţianu, Miruna; Mălan, Abele; Aldinucci, Marco; Birke, Robert; Chen, Lydia is a scholarly article available to read on EtoBox.

What is DALLMi: Domain Adaption for LLM-based Multi-label Classifier about?

Large language models (LLMs) increasingly serve as the backbone for classifying text associated with distinct domains and simultaneously several labels (classes). When encountering domain shifts, e.g., classifier of movie reviews from IMDb to Rotten Tomatoes, adapting such an LLM-based multi-label classifier is challenging due to incomplete label sets at the target domain and daunting training overhead. The existing domain adaptation methods address either image multi-label classifiers or text binary classifiers. In this paper, we design DALLMi, Domain Adaptation Large Language Model interpolator, a first-of-its-kind semi-supervised domain adaptation method for text data models based on LLMs, specifically BERT. The core of DALLMi is the novel variation loss and MixUp regularization, which jointly leverage the limited positively labeled and large quantity of unlabeled text and, importantly, their interpolation from the BERT word embeddings. DALLMi also introduces a label-balanced sampling strategy to overcome the imbalance between labeled and unlabeled data. We evaluate DALLMi against the partial-supervised and unsupervised approach on three datasets under different scenarios of lab

Author

Beţianu, Miruna; Mălan, Abele; Aldinucci, Marco; Birke, Robert; Chen, Lydia

Published

2024

Language

EN