English

ITLC at SemEval-2026 Task 11: Normalization and Deterministic Parsing for Formal Reasoning in LLMs

Computation and Language 2026-05-12 v2 Artificial Intelligence

Abstract

Large language models suffer from content effects in reasoning tasks, particularly in multi-lingual contexts. We introduce a novel method that reduces these biases through explicit structural abstraction that transforms syllogisms into canonical logical representations and applies deterministic parsing to determine validity. Evaluated on the SemEval-2026 Task 11 multilingual benchmark, our approach achieves top-5 rankings across all subtasks while substantially reducing content effects and offering a competitive alternative to complex fine-tuning or activation-level interventions.

Keywords

Cite

@article{arxiv.2603.02676,
  title  = {ITLC at SemEval-2026 Task 11: Normalization and Deterministic Parsing for Formal Reasoning in LLMs},
  author = {Wicaksono Leksono Muhamad and Joanito Agili Lopo and Tack Hwa Wong and Muhammad Ravi Shulthan Habibi and Samuel Cahyawijaya},
  journal= {arXiv preprint arXiv:2603.02676},
  year   = {2026}
}
R2 v1 2026-07-01T11:00:33.655Z