@inproceedings{m-etal-2025-arise,
title = "{ARISE}: Iterative Rule Induction and Synthetic Data Generation for Text Classification",
author = "M, Yaswanth and
Singh, Vaibhav and
Maheshwari, Ayush and
Krishna, Amrith and
Ramakrishnan, Ganesh",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.359/",
doi = "10.18653/v1/2025.findings-naacl.359",
pages = "6419--6434",
ISBN = "979-8-89176-195-7",
abstract = "We propose ARISE, a framework that iteratively induces rules and generates synthetic data for text classification. We combine synthetic data generation and automatic rule induction, via bootstrapping, to iteratively filter the generated rules and data. We induce rules via inductive generalisation of syntactic-ngrams, enabling us to capture a complementary source of supervision. These rules alone lead to performance gains in both, in-context learning (ICL) and fine-tuning (FT) settings. Similarly, use of augmented data from ARISE alone improves the performance for a model, outperforming configurations that rely on complex methods like contrastive learning. Further, our extensive experiments on various datasets covering three full-shot, eight few-shot and seven multilingual variant settings demonstrate that the rules and data we generate lead to performance improvements across these diverse domains and languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="m-etal-2025-arise">
<titleInfo>
<title>ARISE: Iterative Rule Induction and Synthetic Data Generation for Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaswanth</namePart>
<namePart type="family">M</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vaibhav</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayush</namePart>
<namePart type="family">Maheshwari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amrith</namePart>
<namePart type="family">Krishna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ganesh</namePart>
<namePart type="family">Ramakrishnan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>We propose ARISE, a framework that iteratively induces rules and generates synthetic data for text classification. We combine synthetic data generation and automatic rule induction, via bootstrapping, to iteratively filter the generated rules and data. We induce rules via inductive generalisation of syntactic-ngrams, enabling us to capture a complementary source of supervision. These rules alone lead to performance gains in both, in-context learning (ICL) and fine-tuning (FT) settings. Similarly, use of augmented data from ARISE alone improves the performance for a model, outperforming configurations that rely on complex methods like contrastive learning. Further, our extensive experiments on various datasets covering three full-shot, eight few-shot and seven multilingual variant settings demonstrate that the rules and data we generate lead to performance improvements across these diverse domains and languages.</abstract>
<identifier type="citekey">m-etal-2025-arise</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.359</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.359/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>6419</start>
<end>6434</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ARISE: Iterative Rule Induction and Synthetic Data Generation for Text Classification
%A M, Yaswanth
%A Singh, Vaibhav
%A Maheshwari, Ayush
%A Krishna, Amrith
%A Ramakrishnan, Ganesh
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F m-etal-2025-arise
%X We propose ARISE, a framework that iteratively induces rules and generates synthetic data for text classification. We combine synthetic data generation and automatic rule induction, via bootstrapping, to iteratively filter the generated rules and data. We induce rules via inductive generalisation of syntactic-ngrams, enabling us to capture a complementary source of supervision. These rules alone lead to performance gains in both, in-context learning (ICL) and fine-tuning (FT) settings. Similarly, use of augmented data from ARISE alone improves the performance for a model, outperforming configurations that rely on complex methods like contrastive learning. Further, our extensive experiments on various datasets covering three full-shot, eight few-shot and seven multilingual variant settings demonstrate that the rules and data we generate lead to performance improvements across these diverse domains and languages.
%R 10.18653/v1/2025.findings-naacl.359
%U https://aclanthology.org/2025.findings-naacl.359/
%U https://doi.org/10.18653/v1/2025.findings-naacl.359
%P 6419-6434
Markdown (Informal)
[ARISE: Iterative Rule Induction and Synthetic Data Generation for Text Classification](https://aclanthology.org/2025.findings-naacl.359/) (M et al., Findings 2025)
ACL