DALLMi: Domain Adaption for LLM-based Multi-label Classifier

arXiv:2405.01883v1 Announce Type: cross
Abstract: 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 …

abstract arxiv classifier cs.cl cs.lg domain domains labels language language models large language large language models llm llms movie movıe reviews serve text type