Model Releases
Ontology-Guided Neuro-Symbolic Inference: Grounding Language Models with Mathematical Domain Knowledge
arXiv:2602.17826v2 Announce Type: replace Abstract: Language models exhibit fundamental limitations -- hallucination, brittleness, and lack of formal grounding -- that are particularly problematic in
arXiv:2602.17826v2 Announce Type: replace Abstract: Language models exhibit fundamental limitations -- hallucination, brittleness, and lack of formal grounding -- that are particularly problematic in high-stakes specialist fields requiring verifiable reasoning. I investigate whether formal domain ontologies can enhance language model reliability through retrieval-augmented generation. Using mathematics as proof of concept, I implement a neuro-symbolic pipeline leveraging the OpenMath ontology with hybrid retrieval and cross-encoder reranking to inject relevant definitions into model prompts. Evaluation on the MATH benchmark with three open-source models reveals that ontology-guided context improves performance when retrieval quality is high, but irrelevant context actively degrades it -- highlighting both the promise and challenges of neuro-symbolic approaches.
Related
- OntoLogX: Ontology-Guided Knowledge Graph Extraction from Cybersecurity Logs with Large Language Models
- BioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning
- From Errors to Proofs: Minimal-Core-Guided Repair for Neuro-Symbolic Constraint Solving
- TopoAlign: A Framework for Aligning Code to Math via Topological Decomposition
- LEAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks
Source: arXiv cs.AI | 2026-09-02