Iterative Repair with Weak Verifiers for Few-shot Transfer in KBQA with Unanswerability
This work addresses the challenge of handling unanswerable questions in real-world KBQA applications with limited labeled data, representing an incremental improvement over existing methods.
The paper tackles the problem of few-shot knowledge base question answering (KBQA) with unanswerable questions, proposing a new task and datasets, and introduces FUn-FuSIC, which significantly outperforms adapted state-of-the-art models on this task while also setting a new state-of-the-art for answerable few-shot transfer.
Real-world applications of KBQA require models to handle unanswerable questions with a limited volume of in-domain labeled training data. We propose the novel task of few-shot transfer for KBQA with unanswerable questions and contribute two new datasets for performance evaluation. We present FUn-FuSIC - a novel solution for our task that extends FuSIC KBQA, the state-of-the-art few-shot transfer model for answerable-only KBQA. We first note that FuSIC-KBQA's iterative repair makes a strong assumption that all questions are unanswerable. As a remedy, we propose Feedback for Unanswerability (FUn), which uses iterative repair using feedback from a suite of strong and weak verifiers, and an adaptation of self consistency for unanswerabilty to better assess the answerability of a question. Our experiments show that FUn-FuSIC significantly outperforms suitable adaptations of multiple LLM based and supervised SoTA models on our task, while establishing a new SoTA for answerable few-shot transfer as well.