Consistency of LLMs to Comparative Statements in Mathematical Reasoning Tasks

Aidan W. San, Daniel Juyoung Son, Xiaodong Liu, Yangfeng Ji


Abstract
Large language models (LLMs) have the potential to significantly expand access to quality education through applications such as mathematics tutoring. However, a key challenge is that student writing often contains redundancies, and prior research has shown that LLMs can be sensitive to such irrelevant information. This raises a critical research question: How consistent are LLMs when faced with extraneous comparative statements? To address this, we propose a systematic framework for evaluating LLM consistency. Our approach involves a hybrid strategy that integrates template-based and model-based methods to generate comparative statements (e.g., “One of the apples was tastier than average”) and insert them into mathematical reasoning problems. The merit of our approach lies in its systematic and automated nature, enabling rigorous assessment across various models and datasets. Conducting experiments on the GSM8K, AQuA, and Hendrycks MATH benchmarks with a suite of open-source LLMs, we highlight two key results. First, LLM accuracy can drop by over 30% when presented with these statements. Furthermore, we uncover a trade-off between the diversity of the generated statements and the magnitude of the performance drop, where less diverse and more repetitive perturbations lead to greater accuracy degradation.
Anthology ID:
2026.lrec-1.351
Volume:
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:
LREC
SIG:
Publisher:
ELRA Language Resource Association
Note:
Pages:
4482–4496
Language:
External URL:
https://lrec.elra.info/lrec2026-main-351
DOI:
10.63317/5c2k786wu6jm
Bibkey:
Cite (ACL):
Aidan W. San, Daniel Juyoung Son, Xiaodong Liu, and Yangfeng Ji. 2026. Consistency of LLMs to Comparative Statements in Mathematical Reasoning Tasks. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 4482–4496, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
Consistency of LLMs to Comparative Statements in Mathematical Reasoning Tasks (San et al., LREC 2026)
Copy Citation: