SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.17706 · 2024

A Large Language Model Guided Topic Refinement Mechanism for Short Text Modeling

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Modeling topics effectively in short texts, such as tweets and news snippets, is crucial to capturing rapidly evolving social trends. Existing topic models often struggle to accurately capture the underlying semantic patterns of short texts, primarily due to the sparse nature of such data. This nature of texts leads to an unavoidable lack of co-occurrence information, which hinders the coherence and granularity of mined topics. This paper introduces a novel model-agnostic mechanism, termed Topic Refinement, which leverages the advanced text comprehension capabilities of Large Language Models (LLMs) for short-text topic modeling. Unlike traditional methods, this post-processing mechanism enhances the quality of topics extracted by various topic modeling methods through prompt engineering. We guide LLMs in identifying semantically intruder words within the extracted topics and suggesting coherent alternatives to replace these words. This process mimics human-like identification, evaluation, and refinement of the extracted topics. Extensive experiments on four diverse datasets demonstrate that Topic Refinement boosts the topic quality and improves the performance in topic-related text classification tasks.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.17706")
get_code_for_paper("2403.17706")
have("2403.17706")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2403.17706.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2403.17706.svg)](https://syntology.ai/paper/2403.17706)

Connect an agent — have() is free.