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

2026-03-03

AI Summary

This work addresses the susceptibility of large language models (LLMs) to content effects in multilingual logical reasoning, which often induces reasoning biases. To mitigate this issue, the authors propose a lightweight approach that transforms syllogisms into standardized logical forms through structured abstraction and leverages deterministic parsing to assess inferential validity—eliminating the need for complex fine-tuning or activation-based interventions. The method substantially reduces content-induced bias and enhances cross-lingual logical consistency. Evaluated on the SemEval-2026 Task 11 multilingual benchmark, it achieves top-five performance across all subtasks, demonstrating its effectiveness in strengthening the formal reasoning capabilities of LLMs without extensive model modifications.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

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.

Problem

• content effects
• reasoning tasks
• large language models
• multilingual contexts
• logical reasoning

Innovation

• structural abstraction
• deterministic parsing
• formal reasoning
• content effects
• canonical logical representation