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%.
@article{arxiv.2310.02166,
title = {Large Language Models Meet Knowledge Graphs to Answer Factoid Questions},
author = {Mikhail Salnikov and Hai Le and Prateek Rajput and Irina Nikishina and Pavel Braslavski and Valentin Malykh and Alexander Panchenko},
journal= {arXiv preprint arXiv:2310.02166},
year = {2023}
}