Quebec Automobile Insurance Question-Answering With Retrieval-Augmented Generation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Beauchemin, David, Gagnon, Zachary, Khoury, Ricahrd
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909346888155136
author Beauchemin, David
Gagnon, Zachary
Khoury, Ricahrd
author_facet Beauchemin, David
Gagnon, Zachary
Khoury, Ricahrd
contents Large Language Models (LLMs) perform outstandingly in various downstream tasks, and the use of the Retrieval-Augmented Generation (RAG) architecture has been shown to improve performance for legal question answering (Nuruzzaman and Hussain, 2020; Louis et al., 2024). However, there are limited applications in insurance questions-answering, a specific type of legal document. This paper introduces two corpora: the Quebec Automobile Insurance Expertise Reference Corpus and a set of 82 Expert Answers to Layperson Automobile Insurance Questions. Our study leverages both corpora to automatically and manually assess a GPT4-o, a state-of-the-art LLM, to answer Quebec automobile insurance questions. Our results demonstrate that, on average, using our expertise reference corpus generates better responses on both automatic and manual evaluation metrics. However, they also highlight that LLM QA is unreliable enough for mass utilization in critical areas. Indeed, our results show that between 5% to 13% of answered questions include a false statement that could lead to customer misunderstanding.
format Preprint
id arxiv_https___arxiv_org_abs_2410_09623
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Quebec Automobile Insurance Question-Answering With Retrieval-Augmented Generation
Beauchemin, David
Gagnon, Zachary
Khoury, Ricahrd
Computation and Language
Large Language Models (LLMs) perform outstandingly in various downstream tasks, and the use of the Retrieval-Augmented Generation (RAG) architecture has been shown to improve performance for legal question answering (Nuruzzaman and Hussain, 2020; Louis et al., 2024). However, there are limited applications in insurance questions-answering, a specific type of legal document. This paper introduces two corpora: the Quebec Automobile Insurance Expertise Reference Corpus and a set of 82 Expert Answers to Layperson Automobile Insurance Questions. Our study leverages both corpora to automatically and manually assess a GPT4-o, a state-of-the-art LLM, to answer Quebec automobile insurance questions. Our results demonstrate that, on average, using our expertise reference corpus generates better responses on both automatic and manual evaluation metrics. However, they also highlight that LLM QA is unreliable enough for mass utilization in critical areas. Indeed, our results show that between 5% to 13% of answered questions include a false statement that could lead to customer misunderstanding.
title Quebec Automobile Insurance Question-Answering With Retrieval-Augmented Generation
topic Computation and Language
url https://arxiv.org/abs/2410.09623