Details

Autor(en) / Beteiligte

• Li, Zhidong
• Wang, Licai
• Luo, Qibin
• Qiao, Silong

Titel

Large Language Model Based on Full-Text Retrieval for Temporal Knowledge Q&A Approach

Ist Teil von

• 2024 5th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT), 2024, p.441-446

Ort / Verlag

IEEE

Erscheinungsjahr

2024

Quelle

IEEE Electronic Library Online

Beschreibungen/Notizen

• Knowledge Q&A is one of the hot research topics in the field of natural language processing, and temporal knowledge Q&A is a difficult area of Q&A reasoning because it also needs to consider the temporal relationship of knowledge. Today's research usually focuses on the word vector similarity between knowledge and questions as an important basis for answering, while ignoring the sentence granularity semantic information embedded in the knowledge. In this paper, we propose a method of temporal knowledge Q&A for large language models based on full-text retrieval, firstly, the sentence granularity knowledge recall is performed by Elasticsearch so that large language models can learn the knowledge that is highly relevant to the problem, and then verify the temporal knowledge Q&A ability of large language models under Zero-shot, One-shot and Few-shot. The experiments were conducted on the ICEWS05-15 dataset, and the accuracy of answers was significantly improved, demonstrating the effectiveness of the temporal knowledge Q&A method for large language models based on Elasticsearch.