Dynamic Few-Shot Learning for Knowledge Graph Question Answering
This addresses a key bottleneck in applying large language models to knowledge graph querying, offering a generally applicable solution for improved generalization.
The paper tackles the problem of limited out-of-domain generalization in knowledge graph question answering by introducing Dynamic Few-Shot Learning, which achieves state-of-the-art performance across multiple benchmarks.
Large language models present opportunities for innovative Question Answering over Knowledge Graphs (KGQA). However, they are not inherently designed for query generation. To bridge this gap, solutions have been proposed that rely on fine-tuning or ad-hoc architectures, achieving good results but limited out-of-domain distribution generalization. In this study, we introduce a novel approach called Dynamic Few-Shot Learning (DFSL). DFSL integrates the efficiency of in-context learning and semantic similarity and provides a generally applicable solution for KGQA with state-of-the-art performance. We run an extensive evaluation across multiple benchmark datasets and architecture configurations.