@inproceedings{hayat-etal-2026-numbers,
title = "From Numbers to Narratives: Efficient Language Model-Based Detection for Safety-Critical Minority Classes",
author = "Hayat, Ahatsham and
Tridle, Hunter and
Hasan, Mohammad Rashedul",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-eacl.258/",
pages = "4920--4937",
ISBN = "979-8-89176-386-9",
abstract = "Safety-critical classification tasks face a persistent challenge: traditional models achieve high overall accuracy but inadequate performance on critical minority classes. We introduce a numbers to narratives framework that transforms tabular data into contextually rich descriptions, enabling language models to leverage pre-trained knowledge for minority class detection. Our approach integrates structured verbalization, linguistically-informed augmentation, and parameter-efficient fine-tuning to address the ``minority class blind spot'' in high-consequence domains. Using a significantly more efficient model architecture than existing approaches, our framework achieves superior minority class F1-scores: 78.76{\%} for machine failures (+7.42 points over XGBoost), 65.87{\%} for at-risk students (+12.12 points over MLP), and 32.00{\%} for semiconductor failures (+1.01 points over XGBoost, despite 14:1 class imbalance). Our approach also improves overall accuracy by up to 22.43{\%} in five of six datasets while maintaining computational feasibility. Ablation studies confirm that narrative-based verbalization enables effective reasoning about tabular data by contextualizing abstract numerical features. This work provides a practical, resource-efficient approach for enhancing minority class performance in safety-critical domains."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hayat-etal-2026-numbers">
<titleInfo>
<title>From Numbers to Narratives: Efficient Language Model-Based Detection for Safety-Critical Minority Classes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahatsham</namePart>
<namePart type="family">Hayat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hunter</namePart>
<namePart type="family">Tridle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Rashedul</namePart>
<namePart type="family">Hasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-386-9</identifier>
</relatedItem>
<abstract>Safety-critical classification tasks face a persistent challenge: traditional models achieve high overall accuracy but inadequate performance on critical minority classes. We introduce a numbers to narratives framework that transforms tabular data into contextually rich descriptions, enabling language models to leverage pre-trained knowledge for minority class detection. Our approach integrates structured verbalization, linguistically-informed augmentation, and parameter-efficient fine-tuning to address the “minority class blind spot” in high-consequence domains. Using a significantly more efficient model architecture than existing approaches, our framework achieves superior minority class F1-scores: 78.76% for machine failures (+7.42 points over XGBoost), 65.87% for at-risk students (+12.12 points over MLP), and 32.00% for semiconductor failures (+1.01 points over XGBoost, despite 14:1 class imbalance). Our approach also improves overall accuracy by up to 22.43% in five of six datasets while maintaining computational feasibility. Ablation studies confirm that narrative-based verbalization enables effective reasoning about tabular data by contextualizing abstract numerical features. This work provides a practical, resource-efficient approach for enhancing minority class performance in safety-critical domains.</abstract>
<identifier type="citekey">hayat-etal-2026-numbers</identifier>
<location>
<url>https://aclanthology.org/2026.findings-eacl.258/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>4920</start>
<end>4937</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Numbers to Narratives: Efficient Language Model-Based Detection for Safety-Critical Minority Classes
%A Hayat, Ahatsham
%A Tridle, Hunter
%A Hasan, Mohammad Rashedul
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F hayat-etal-2026-numbers
%X Safety-critical classification tasks face a persistent challenge: traditional models achieve high overall accuracy but inadequate performance on critical minority classes. We introduce a numbers to narratives framework that transforms tabular data into contextually rich descriptions, enabling language models to leverage pre-trained knowledge for minority class detection. Our approach integrates structured verbalization, linguistically-informed augmentation, and parameter-efficient fine-tuning to address the “minority class blind spot” in high-consequence domains. Using a significantly more efficient model architecture than existing approaches, our framework achieves superior minority class F1-scores: 78.76% for machine failures (+7.42 points over XGBoost), 65.87% for at-risk students (+12.12 points over MLP), and 32.00% for semiconductor failures (+1.01 points over XGBoost, despite 14:1 class imbalance). Our approach also improves overall accuracy by up to 22.43% in five of six datasets while maintaining computational feasibility. Ablation studies confirm that narrative-based verbalization enables effective reasoning about tabular data by contextualizing abstract numerical features. This work provides a practical, resource-efficient approach for enhancing minority class performance in safety-critical domains.
%U https://aclanthology.org/2026.findings-eacl.258/
%P 4920-4937
Markdown (Informal)
[From Numbers to Narratives: Efficient Language Model-Based Detection for Safety-Critical Minority Classes](https://aclanthology.org/2026.findings-eacl.258/) (Hayat et al., Findings 2026)
ACL