Work

HHU-SyLo at SemEval-2026 Task 11: Logic in the Loop – Hybridizing LLMs and Theorem Provers for Robust Formal Reasoning

Year: 2026

Type: conference-paper

Abstract: We present our system for SemEval-2026 Task 11 on reasoning disentanglement, separating syllogistic validity from semantic plausibility.We compare direct neural inference against two neuro-symbolic pipelines: translation to firstorder logic and to syllogistic triples.By offloading inference to symbolic theorem provers, these hybrid models effectively mitigate content bias and improve logical fidelity.

Source: International Workshop on Semantic Evaluation (SemEval)

DOI: 10.18653/v1/2026.semeval-1.400

Authors: Wiebke Petersen, Cherine Jaziri, Diem Tran

Institution: Heinrich Heine University Düsseldorf

Language: English

Topic: Logic, Reasoning, and Knowledge

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: Heinrich-Heine-Universität Düsseldorf

OpenAlex ID: W7166869954