English

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

Computation and Language 2024-06-14 v3 Artificial Intelligence

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 input for LLM few-shot in-context learning to generate logical forms. These are further refined using execution-guided feedback. Experiments over multiple source-target KBQA pairs of varying complexity show that FuSIC-KBQA significantly outperforms adaptations of SoTA KBQA models for this setting. Additional experiments show that FuSIC-KBQA also outperforms SoTA KBQA models in the in-domain setting when training data is limited.

Keywords

Cite

@article{arxiv.2311.08894,
  title  = {Few-shot Transfer Learning for Knowledge Base Question Answering: Fusing Supervised Models with In-Context Learning},
  author = {Mayur Patidar and Riya Sawhney and Avinash Singh and Biswajit Chatterjee and Mausam and Indrajit Bhattacharya},
  journal= {arXiv preprint arXiv:2311.08894},
  year   = {2024}
}

Comments

ACL-2024 camera-ready version

R2 v1 2026-06-28T13:21:59.346Z