Proofbusters at SemEval-2026 Task 11: Neuro-Symbolic Syllogistic Reasoning via LLM-Guided Structure Extraction and Deterministic Validation

Mohamed Ayman, Khaled Marzouk, Abdallah Mashaly, Ahmed Hereiz


Abstract
This paper describes our system for SemEval-2026 Task 11, which evaluates whether language models can perform formal syllogistic reasoning independent of semantic content. Drawing inspiration from Euler’s abstraction in the Königsberg bridges problem where geographical details were stripped away to reveal pure graph structure, three symbolic abstraction strategies are explored to eliminate belief bias. First, terms are replaced with generic placeholders by template abstraction. Second, entities are mapped into explicit constraint-tracking structures by object-oriented abstraction. Third, statements are translated into mathematical set notation by set-theoretic abstraction, with existential import constraints enforced to align with Aristotelian logic. Using Gemini Flash 2.5 and Pro 2.5, the set-theoretic approach achieves 98.95% accuracy with a content bias (TCE) of 2.13 on the English sub-task (overall score: 46.23). Results demonstrate that deeper mathematical abstraction fully stripping semantic content and leveraging formal set notation substantially outperforms template-based approaches in mitigating belief bias, though challenges remain in multi-step constraint composition.
Anthology ID:
2026.semeval-1.182
Volume:
Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
Month:
July
Year:
2026
Address:
San Diego, California, USA
Editors:
Ekaterina Kochmar, Debanjan Ghosh, Kai North, Mamoru Komachi, Marcos Zampieri
Venues:
SemEval | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1407–1415
Language:
URL:
https://aclanthology.org/2026.semeval-1.182/
DOI:
10.18653/v1/2026.semeval-1.182
Bibkey:
Cite (ACL):
Mohamed Ayman, Khaled Marzouk, Abdallah Mashaly, and Ahmed Hereiz. 2026. Proofbusters at SemEval-2026 Task 11: Neuro-Symbolic Syllogistic Reasoning via LLM-Guided Structure Extraction and Deterministic Validation. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 1407–1415, San Diego, California, USA. Association for Computational Linguistics.
Cite (Informal):
Proofbusters at SemEval-2026 Task 11: Neuro-Symbolic Syllogistic Reasoning via LLM-Guided Structure Extraction and Deterministic Validation (Ayman et al., SemEval 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.semeval-1.182.pdf
Supplementarymaterial:
 2026.semeval-1.182.SupplementaryMaterial.zip