@inproceedings{aljanaideh-ganideh-2026-llm,
title = "{LLM}-induced Rationales for More Compact Explainable Style Classification Models",
author = "Aljanaideh, Ahmad and
Ganideh, Saeb",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1426/",
doi = "10.18653/v1/2026.findings-acl.1426",
pages = "28571--28577",
ISBN = "979-8-89176-395-1",
abstract = "The complexity of recent natural language classification models led to interest in developing methods for improving the performance of explainable models (e.g. Logistic Regression). Existing methods focus on clustering word embeddings to discover fine-grained contextual features that can be used to train a linear model. While those methods help reduce the gap in performance between black-box models and explainable models, they are based on discovering a large number of features, and this affects interpretability. In this work, we propose a model that leverages Large Language Models (LLMs) and clustering algorithms to discover a compact set of interpretable features. The proposed model first uses GPT-4o mini to extract rationales (i.e. phrases which explain an item{'}s label) from labeled text, and then clusters those rationales to obtain a compact, interpretable feature space. Across 3 Style Classification tasks, the resulting features achieve comparable performance to word-cluster baselines on most tasks, while reducing the number of features by 85{--}99{\%}. These results highlight the potential of LLMs to improve the compactness of explainable AI models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aljanaideh-ganideh-2026-llm">
<titleInfo>
<title>LLM-induced Rationales for More Compact Explainable Style Classification Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmad</namePart>
<namePart type="family">Aljanaideh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saeb</namePart>
<namePart type="family">Ganideh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>The complexity of recent natural language classification models led to interest in developing methods for improving the performance of explainable models (e.g. Logistic Regression). Existing methods focus on clustering word embeddings to discover fine-grained contextual features that can be used to train a linear model. While those methods help reduce the gap in performance between black-box models and explainable models, they are based on discovering a large number of features, and this affects interpretability. In this work, we propose a model that leverages Large Language Models (LLMs) and clustering algorithms to discover a compact set of interpretable features. The proposed model first uses GPT-4o mini to extract rationales (i.e. phrases which explain an item’s label) from labeled text, and then clusters those rationales to obtain a compact, interpretable feature space. Across 3 Style Classification tasks, the resulting features achieve comparable performance to word-cluster baselines on most tasks, while reducing the number of features by 85–99%. These results highlight the potential of LLMs to improve the compactness of explainable AI models.</abstract>
<identifier type="citekey">aljanaideh-ganideh-2026-llm</identifier>
<identifier type="doi">10.18653/v1/2026.findings-acl.1426</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1426/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>28571</start>
<end>28577</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLM-induced Rationales for More Compact Explainable Style Classification Models
%A Aljanaideh, Ahmad
%A Ganideh, Saeb
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F aljanaideh-ganideh-2026-llm
%X The complexity of recent natural language classification models led to interest in developing methods for improving the performance of explainable models (e.g. Logistic Regression). Existing methods focus on clustering word embeddings to discover fine-grained contextual features that can be used to train a linear model. While those methods help reduce the gap in performance between black-box models and explainable models, they are based on discovering a large number of features, and this affects interpretability. In this work, we propose a model that leverages Large Language Models (LLMs) and clustering algorithms to discover a compact set of interpretable features. The proposed model first uses GPT-4o mini to extract rationales (i.e. phrases which explain an item’s label) from labeled text, and then clusters those rationales to obtain a compact, interpretable feature space. Across 3 Style Classification tasks, the resulting features achieve comparable performance to word-cluster baselines on most tasks, while reducing the number of features by 85–99%. These results highlight the potential of LLMs to improve the compactness of explainable AI models.
%R 10.18653/v1/2026.findings-acl.1426
%U https://aclanthology.org/2026.findings-acl.1426/
%U https://doi.org/10.18653/v1/2026.findings-acl.1426
%P 28571-28577
Markdown (Informal)
[LLM-induced Rationales for More Compact Explainable Style Classification Models](https://aclanthology.org/2026.findings-acl.1426/) (Aljanaideh & Ganideh, Findings 2026)
ACL