LB-KBQA: Large-language-model and BERT based Knowledge-Based Question and Answering System
This work addresses intent recognition challenges in KBQA systems, particularly for financial domain applications, but appears incremental as it builds on existing LLM and BERT methods.
The authors tackled the problem of intent recognition in Knowledge-Based Question Answering (KBQA) systems, which is hindered by linguistic diversity and new intents, by proposing LB-KBQA, a system combining a Large Language Model (LLM) and BERT, and demonstrated superior effectiveness in financial domain question answering experiments.
Generative Artificial Intelligence (AI), because of its emergent abilities, has empowered various fields, one typical of which is large language models (LLMs). One of the typical application fields of Generative AI is large language models (LLMs), and the natural language understanding capability of LLM is dramatically improved when compared with conventional AI-based methods. The natural language understanding capability has always been a barrier to the intent recognition performance of the Knowledge-Based-Question-and-Answer (KBQA) system, which arises from linguistic diversity and the newly appeared intent. Conventional AI-based methods for intent recognition can be divided into semantic parsing-based and model-based approaches. However, both of the methods suffer from limited resources in intent recognition. To address this issue, we propose a novel KBQA system based on a Large Language Model(LLM) and BERT (LB-KBQA). With the help of generative AI, our proposed method could detect newly appeared intent and acquire new knowledge. In experiments on financial domain question answering, our model has demonstrated superior effectiveness.