Quebec Automobile Insurance Question-Answering With Retrieval-Augmented Generation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| 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 |