---
title: "Neuro-Symbolic Logical Reasoning with Textual Entailment"
authors:
  - "Zacchary Sadeddine"
  - "Fabian Suchanek"
doi: "10.24963/ijcai.2026/989"
url: "https://ijcai.org/proceedings/2026/989"
pdf: "https://ijcai.org/proceedings/2026/0989.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "8501-8504"
track: "Demo Track"
keywords:
  - "AI: Natural Language Processing"
  - "AI: Knowledge Representation and Reasoning"
---

# Neuro-Symbolic Logical Reasoning with Textual Entailment

Zacchary Sadeddine, Fabian Suchanek

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 8501-8504. DOI: [10.24963/ijcai.2026/989](https://doi.org/10.24963/ijcai.2026/989)

## Abstract

Large Language Models can use logical deduction to answer natural language questions, but they remain black-boxes with potentially erroneous chains-of-thought. In this paper, we adapt VANESSA, a neuro-symbolic method for chain-of-thought verification, to reasoning-based question answering. VANESSA combines a logical reasoner with a neural textual entailment model to handle phrasing variations. Building on VANESSA, we develop a transparent, logic-based approach to answer natural language questions even with phrase variations. Our experiments across various datasets show our method is competitive with the state of the art, while also delivering proof trees for its answers. A demo interface allows users to interact with the system.