| Shafiei, Mohammadamin, Saffari, Hamidreza, Pilehvar, Mohammad Taher and Raganato, Alessandro 2026. TruthTrap: A bilingual benchmark for evaluating factually correct yet misleading information in question answering. Presented at: EACL, Rabat, Morocco, 24-29 March 2026. Published in: Demberg, Vera, Inui, Kentaro and Marquez, Lluis eds. Findings of the Association for Computational Linguistics: EACL 2026. Association for Computational Linguistics, pp. 2966-2987. 10.18653/v1/2026.findings-eacl.155 |
Abstract
Large Language Models (LLMs) are increasingly used to answer factual, information-seeking questions (ISQs). While prior work often focuses on false, misleading information, little attention has been paid to true but strategically persuasive content that can derail a model’s reasoning. To address this gap, we introduce a new evaluation dataset, TruthTrap, in two languages, i.e., English and Farsi, on Iran-related ISQs, each paired with a correct explanation and a persuasive-yet-misleading true hint. We then evaluate nine diverse LLMs (spanning proprietary and open-source systems) via factuality classification and multiple-choice QA tasks, finding that accuracy drops by 25%, on average, when models encounter these misleading yet factual hints. Also, the models’ predictions match the hint-aligned options up to 77 percent of the time. Notably, models often misjudge such hints in isolation yet still integrate them into final answers. Our results highlight a significant limitation in LLM outputs, underscoring the importance of robust fact-verification and emphasizing real-world risks posed by partial truths in domains like social media, education, and policy-making.
| Item Type: | Conference or Workshop Item - published (Paper) |
|---|---|
| Date Type: | Publication |
| Status: | Published |
| Schools: | Schools > Computer Science & Informatics |
| Publisher: | Association for Computational Linguistics |
| ISBN: | 9798891763869 |
| Last Modified: | 02 Aug 2026 01:19 |
| URI: | https://orca.cardiff.ac.uk/id/eprint/187345 |
Actions (repository staff only)
 |
Edit Item |
Dimensions
Dimensions