MétaCan
Menu
Back to cohort
Record W4404781236 · doi:10.18653/v1/2024.nllp-1.5

Quebec Automobile Insurance Question-Answering With Retrieval-Augmented Generation

2024· article· en· W4404781236 on OpenAlexafffundabout
David Beauchemin, Richard Khoury, Zachary Gagnon

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsUniversité Laval
FundersFonds de recherche du Québec – Nature et technologiesNatural Sciences and Engineering Research Council of Canada
KeywordsQuestion answeringAutomobile insuranceComputer scienceInformation retrievalBusinessActuarial science

Abstract

fetched live from OpenAlex

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.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.013
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.379
Threshold uncertainty score0.763

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.013
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0030.002
Science and technology studies0.0020.001
Scholarly communication0.0010.002
Open science0.0020.002
Research integrity0.0020.001
Insufficient payload (model declined to judge)0.0180.005

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.015
GPT teacher head0.250
Teacher spread0.235 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations2
Published2024
Admission routes3
Has abstractyes

Explore more

Same topicTopic ModelingFrench-language works237,207