Large Language Models Meet Knowledge Graphs to Answer Factoid Questions
This work addresses the challenge of enhancing factoid question answering for NLP applications, but it is incremental as it builds on existing methods with specific optimizations.
The paper tackles the problem of answering factoid questions by integrating knowledge graphs with large language models, resulting in a 4-6% improvement in Hits@1 scores through a re-ranking method.
Recently, it has been shown that the incorporation of structured knowledge into Large Language Models significantly improves the results for a variety of NLP tasks. In this paper, we propose a method for exploring pre-trained Text-to-Text Language Models enriched with additional information from Knowledge Graphs for answering factoid questions. More specifically, we propose an algorithm for subgraphs extraction from a Knowledge Graph based on question entities and answer candidates. Then, we procure easily interpreted information with Transformer-based models through the linearization of the extracted subgraphs. Final re-ranking of the answer candidates with the extracted information boosts Hits@1 scores of the pre-trained text-to-text language models by 4-6%.