@inproceedings{nguyen-etal-2026-llm,
title = "{LLM} Feedback for Topic Model with Preference Optimization and Contrastive Learning",
author = "Nguyen, Tung and
Trong, Dat Phan and
Van, Linh Ngo and
Nguyen, Duc Anh and
Hoang, Dinh Thai and
Nguyen, Diep",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.265/",
pages = "6021--6045",
ISBN = "979-8-89176-459-0",
abstract = "The integration of large language models (LLMs) into topic modeling has shown promise for improving topic interpretability and coherence, particularly by exploiting the generative capabilities of LLMs through instruction-based prompting. However, existing methods often incur substantial computational cost and inference complexity. To address these limitations, we propose **LLMFeed**, a novel framework that leverages **feed**back from an **LLM** to improve topic model optimization. Specifically, the LLM is used to **evaluate** topic quality, **identify** semantic meaning, and **recommend** representative topic words. These signals are then incorporated to (i) refine topic representations via Direct Preference Optimization (DPO), and (ii) guide contrastive learning for improved document-topic assignments. Extensive experiments show that **LLMFeed** achieves a 7.6{\%} gain in topic coherence and over 10{\%} improvement in doc-topic distributions on 20 Newsgroups dataset, while requiring only minutes to run, compared with hours for recent LLM-integrated topic modeling methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2026-llm">
<titleInfo>
<title>LLM Feedback for Topic Model with Preference Optimization and Contrastive Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tung</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dat</namePart>
<namePart type="given">Phan</namePart>
<namePart type="family">Trong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linh</namePart>
<namePart type="given">Ngo</namePart>
<namePart type="family">Van</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Duc</namePart>
<namePart type="given">Anh</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dinh</namePart>
<namePart type="given">Thai</namePart>
<namePart type="family">Hoang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diep</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>The integration of large language models (LLMs) into topic modeling has shown promise for improving topic interpretability and coherence, particularly by exploiting the generative capabilities of LLMs through instruction-based prompting. However, existing methods often incur substantial computational cost and inference complexity. To address these limitations, we propose **LLMFeed**, a novel framework that leverages **feed**back from an **LLM** to improve topic model optimization. Specifically, the LLM is used to **evaluate** topic quality, **identify** semantic meaning, and **recommend** representative topic words. These signals are then incorporated to (i) refine topic representations via Direct Preference Optimization (DPO), and (ii) guide contrastive learning for improved document-topic assignments. Extensive experiments show that **LLMFeed** achieves a 7.6% gain in topic coherence and over 10% improvement in doc-topic distributions on 20 Newsgroups dataset, while requiring only minutes to run, compared with hours for recent LLM-integrated topic modeling methods.</abstract>
<identifier type="citekey">nguyen-etal-2026-llm</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.265/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>6021</start>
<end>6045</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLM Feedback for Topic Model with Preference Optimization and Contrastive Learning
%A Nguyen, Tung
%A Trong, Dat Phan
%A Van, Linh Ngo
%A Nguyen, Duc Anh
%A Hoang, Dinh Thai
%A Nguyen, Diep
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F nguyen-etal-2026-llm
%X The integration of large language models (LLMs) into topic modeling has shown promise for improving topic interpretability and coherence, particularly by exploiting the generative capabilities of LLMs through instruction-based prompting. However, existing methods often incur substantial computational cost and inference complexity. To address these limitations, we propose **LLMFeed**, a novel framework that leverages **feed**back from an **LLM** to improve topic model optimization. Specifically, the LLM is used to **evaluate** topic quality, **identify** semantic meaning, and **recommend** representative topic words. These signals are then incorporated to (i) refine topic representations via Direct Preference Optimization (DPO), and (ii) guide contrastive learning for improved document-topic assignments. Extensive experiments show that **LLMFeed** achieves a 7.6% gain in topic coherence and over 10% improvement in doc-topic distributions on 20 Newsgroups dataset, while requiring only minutes to run, compared with hours for recent LLM-integrated topic modeling methods.
%U https://aclanthology.org/2026.emnlp-main.265/
%P 6021-6045
Markdown (Informal)
[LLM Feedback for Topic Model with Preference Optimization and Contrastive Learning](https://aclanthology.org/2026.emnlp-main.265/) (Nguyen et al., EMNLP 2026)
ACL