Skip to main navigation Skip to search Skip to main content

BTC-SAM: Leveraging LLMs for Generation of Bias Test Cases for Sentiment Analysis Models

  • Zsolt T. Kardkovács
  • , Lynda Djennane
  • , Anna Field
  • , Boualem Benatallah
  • , Yacine Gaci
  • , Fabio Casati
  • , Walid Gaaloul
  • Dublin City University
  • École supérieure en Sciences et Technologies de l'Informatique et du Numérique
  • Plus que PRO Lab
  • ServiceNow
  • Università di Trento

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Sentiment Analysis (SA) models harbor inherent social biases that can be harmful in real-world applications. These biases are identified by examining the output of SA models for sentences that only vary in the identity groups of the subjects. Constructing natural, linguistically rich, relevant, and diverse sets of sentences that provide sufficient coverage over the domain is expensive, especially when addressing a wide range of biases: it requires domain experts and/or crowd-sourcing. In this paper, we present a novel bias testing framework, BTC-SAM, which generates high-quality test cases for bias testing in SA models with minimal specification using Large Language Models (LLMs) for the controllable generation of test sentences. Our experiments show that relying on LLMs can provide high linguistic variation and diversity in the test sentences, thereby offering better test coverage compared to base prompting methods even for previously unseen biases.

Original languageEnglish
Title of host publicationEMNLP 2025 - 2025 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
EditorsChristos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
PublisherAssociation for Computational Linguistics (ACL)
Pages15097-15113
Number of pages17
ISBN (Electronic)9798891763326
DOIs
Publication statusPublished - 1 Jan 2025
Event30th Conference on Empirical Methods in Natural Language Processing, EMNLP 2025 - Suzhou, China
Duration: 4 Nov 20259 Nov 2025

Publication series

NameEMNLP 2025 - 2025 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

Conference

Conference30th Conference on Empirical Methods in Natural Language Processing, EMNLP 2025
Country/TerritoryChina
CitySuzhou
Period4/11/259/11/25

Fingerprint

Dive into the research topics of 'BTC-SAM: Leveraging LLMs for Generation of Bias Test Cases for Sentiment Analysis Models'. Together they form a unique fingerprint.

Cite this