Ontology-Guided Neuro-Symbolic Inference: Grounding Language Models with Mathematical Domain Knowledge

작성자

카테고리:

← 피드로
arXiv cs.AI · Marcelo Labre · 2026-09-02 AI

[Submitted on 19 Feb 2026 (v1), last revised 31 Aug 2026 (this version, v2)]

View PDF HTML (experimental)

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.

Submission history

From: Marcelo Labre [view email]
[v1] Thu, 19 Feb 2026 20:45:16 UTC (2,970 KB)
[v2] Mon, 31 Aug 2026 18:34:12 UTC (2,970 KB)

원문에서 계속 ↗

추출 본문 · 출처: arxiv.org · https://arxiv.org/abs/2602.17826