Comprehensive Evaluation of Large Language Models for Topic Modeling

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Doi, Tomoki, Isonuma, Masaru, Yanaka, Hitomi
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909231043575808
author Doi, Tomoki
Isonuma, Masaru
Yanaka, Hitomi
author_facet Doi, Tomoki
Isonuma, Masaru
Yanaka, Hitomi
contents Recent work utilizes Large Language Models (LLMs) for topic modeling, generating comprehensible topic labels for given documents. However, their performance has mainly been evaluated qualitatively, and there remains room for quantitative investigation of their capabilities. In this paper, we quantitatively evaluate LLMs from multiple perspectives: the quality of topics, the impact of LLM-specific concerns, such as hallucination and shortcuts for limited documents, and LLMs' controllability of topic categories via prompts. Our findings show that LLMs can identify coherent and diverse topics with few hallucinations but may take shortcuts by focusing only on parts of documents. We also found that their controllability is limited.
format Preprint
id arxiv_https___arxiv_org_abs_2406_00697
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Comprehensive Evaluation of Large Language Models for Topic Modeling
Doi, Tomoki
Isonuma, Masaru
Yanaka, Hitomi
Computation and Language
Recent work utilizes Large Language Models (LLMs) for topic modeling, generating comprehensible topic labels for given documents. However, their performance has mainly been evaluated qualitatively, and there remains room for quantitative investigation of their capabilities. In this paper, we quantitatively evaluate LLMs from multiple perspectives: the quality of topics, the impact of LLM-specific concerns, such as hallucination and shortcuts for limited documents, and LLMs' controllability of topic categories via prompts. Our findings show that LLMs can identify coherent and diverse topics with few hallucinations but may take shortcuts by focusing only on parts of documents. We also found that their controllability is limited.
title Comprehensive Evaluation of Large Language Models for Topic Modeling
topic Computation and Language
url https://arxiv.org/abs/2406.00697