Conversational Factor Information Retrieval Model (ConFIRM)

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Choi, Stephen, Gazeley, William, Wong, Siu Ho, Li, Tingting
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912063371083776
author Choi, Stephen
Gazeley, William
Wong, Siu Ho
Li, Tingting
author_facet Choi, Stephen
Gazeley, William
Wong, Siu Ho
Li, Tingting
contents This paper introduces the Conversational Factor Information Retrieval Method (ConFIRM), a novel approach to fine-tuning large language models (LLMs) for domain-specific retrieval tasks. ConFIRM leverages the Five-Factor Model of personality to generate synthetic datasets that accurately reflect target population characteristics, addressing data scarcity in specialized domains. We demonstrate ConFIRM's effectiveness through a case study in the finance sector, fine-tuning a Llama-2-7b model using personality-aligned data from the PolyU-Asklora Fintech Adoption Index. The resulting model achieved 91% accuracy in classifying financial queries, with an average inference time of 0.61 seconds on an NVIDIA A100 GPU. ConFIRM shows promise for creating more accurate and personalized AI-driven information retrieval systems across various domains, potentially mitigating issues of hallucinations and outdated information in LLMs deployed
format Preprint
id arxiv_https___arxiv_org_abs_2310_13001
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Conversational Factor Information Retrieval Model (ConFIRM)
Choi, Stephen
Gazeley, William
Wong, Siu Ho
Li, Tingting
Information Retrieval
Artificial Intelligence
Computational Engineering, Finance, and Science
Computation and Language
Machine Learning
This paper introduces the Conversational Factor Information Retrieval Method (ConFIRM), a novel approach to fine-tuning large language models (LLMs) for domain-specific retrieval tasks. ConFIRM leverages the Five-Factor Model of personality to generate synthetic datasets that accurately reflect target population characteristics, addressing data scarcity in specialized domains. We demonstrate ConFIRM's effectiveness through a case study in the finance sector, fine-tuning a Llama-2-7b model using personality-aligned data from the PolyU-Asklora Fintech Adoption Index. The resulting model achieved 91% accuracy in classifying financial queries, with an average inference time of 0.61 seconds on an NVIDIA A100 GPU. ConFIRM shows promise for creating more accurate and personalized AI-driven information retrieval systems across various domains, potentially mitigating issues of hallucinations and outdated information in LLMs deployed
title Conversational Factor Information Retrieval Model (ConFIRM)
topic Information Retrieval
Artificial Intelligence
Computational Engineering, Finance, and Science
Computation and Language
Machine Learning
url https://arxiv.org/abs/2310.13001