Few-shot Transfer Learning for Knowledge Base Question Answering: Fusing Supervised Models with In-Context Learning

arXiv:2311.08894v2 Announce Type: replace
Abstract: Existing Knowledge Base Question Answering (KBQA) architectures are hungry for annotated data, which make them costly and time-consuming to deploy. We introduce the problem of few-shot transfer learning for KBQA, where the target domain offers only a few labeled examples, but a large labeled training dataset is available in a source domain. We propose a novel KBQA architecture called FuSIC-KBQA that performs KB-retrieval using multiple source-trained retrievers, re-ranks using an LLM and uses this as …

abstract annotated data architectures arxiv context cs.ai cs.cl data deploy domain examples few-shot in-context learning knowledge knowledge base question question answering them transfer transfer learning type