Same Meaning, Different Scores: Lexical and Syntactic Sensitivity in LLM Evaluation

Bogdan Kostić, Conor Fallon, Julian Risch, Alexander Loeser


Abstract
The rapid advancement of Large Language Models (LLMs) has established standardized evaluation benchmarks as the primary instrument for model comparison. Yet, their reliability is increasingly questioned due to sensitivity to shallow variations in input prompts. This paper examines how controlled, truth-conditionally equivalent lexical and syntactic perturbations affect the absolute performance and relative ranking of 23 contemporary LLMs across three benchmarks: MMLU, SQuAD, and AMEGA. We employ two linguistically principled pipelines to generate meaning-preserving variations: one performing synonym substitution for lexical changes, and another using dependency parsing to determine applicable syntactic transformations. Results show that lexical perturbations consistently induce substantial, statistically significant performance degradation across nearly all models and tasks, while syntactic perturbations have more heterogeneous effects, occasionally improving results. Both perturbation types destabilize model leaderboards on complex tasks. Furthermore, model robustness did not consistently scale with model size, revealing strong task dependence. Overall, the findings suggest that LLMs rely more on surface-level lexical patterns than on abstract linguistic competence, underscoring the need for robustness testing as a standard component of LLM evaluation.
Anthology ID:
2026.lrec-1.363
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:
4626–4637
Language:
External URL:
https://lrec.elra.info/lrec2026-main-363
DOI:
10.63317/297j5gohq2ip
Bibkey:
Cite (ACL):
Bogdan Kostić, Conor Fallon, Julian Risch, and Alexander Loeser. 2026. Same Meaning, Different Scores: Lexical and Syntactic Sensitivity in LLM Evaluation. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 4626–4637, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
Same Meaning, Different Scores: Lexical and Syntactic Sensitivity in LLM Evaluation (Kostić et al., LREC 2026)
Copy Citation: