Research

Paper

AI LLM March 03, 2026

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

Authors

Wicaksono Leksono Muhamad, Joanito Agili Lopo, Tack Hwa Wong, Muhammad Ravi Shulthan Habibi, Samuel Cahyawijaya

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.

Metadata

arXiv ID: 2603.02676
Provider: ARXIV
Primary Category: cs.CL
Published: 2026-03-03
Fetched: 2026-03-04 03:41

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.02676v1</id>\n    <title>ITLC at SemEval-2026 Task 11: Normalization and Deterministic Parsing for Formal Reasoning in LLMs</title>\n    <updated>2026-03-03T07:02:45Z</updated>\n    <link href='https://arxiv.org/abs/2603.02676v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.02676v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-03T07:02:45Z</published>\n    <arxiv:primary_category term='cs.CL'/>\n    <author>\n      <name>Wicaksono Leksono Muhamad</name>\n    </author>\n    <author>\n      <name>Joanito Agili Lopo</name>\n    </author>\n    <author>\n      <name>Tack Hwa Wong</name>\n    </author>\n    <author>\n      <name>Muhammad Ravi Shulthan Habibi</name>\n    </author>\n    <author>\n      <name>Samuel Cahyawijaya</name>\n    </author>\n  </entry>"
}