Work

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

Year: 2026

Type: conference-paper

Abstract: Large language models suffer from content effects in reasoning tasks, particularly in multilingual 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-6 rankings across all subtasks while substantially reducing content effects and offering a competitive alternative to complex fine-tuning or activation-level interventions.

Source: International Workshop on Semantic Evaluation (SemEval)

DOI: 10.18653/v1/2026.semeval-1.221

Authors: Wicaksono M., Joanito Lopo, Tack Hwa Wong, Muhammad Ravi Shulthan Habibi, Samuel Cahyawijaya

Institutions: Universiti Teknologi Petronas, Cohere (Canada)

Language: English

Topic: Logic, Reasoning, and Knowledge

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W7166877821

FWCI:

Cites:

Cited by:

Related to: 10