• Computer Science > Artificial Intelligence [Submitted on 19 Feb 2026] Title:Ontology-Guided Neuro-Symbolic Inference: Grounding Language Models with Mathematical Domain Knowledge 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. • Current browse context: cs.AI References & Citations export BibTeX citation Loading… • Bibliographic and Citation Tools Bibliographic Explorer (What is the Explorer?) Connected Papers (What is Connected Papers?) Litmaps (What is Litmaps?) scite Smart Citations (What are Smart Citations?) Code, Data and Media Associated with this Article alphaXiv (What is alphaXiv?) CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub (What is DagsHub?) Gotit.pub (Wh
Article Summaries:
- Summary
A recent study explores whether formal domain ontologies can improve the reliability of large language models (LLMs) in specialist tasks. Using the OpenMath ontology, the authors built a neuro‑symbolic pipeline that retrieves relevant mathematical definitions and reranks them with a cross‑encoder before injecting them into model prompts. On the MATH benchmark, three open‑source LLMs showed performance gains when the retrieved context was accurate, but the models suffered when irrelevant or noisy definitions were included. The results underscore both the potential of ontology‑guided grounding for reducing hallucinations and the sensitivity of LLMs to the quality of external knowledge.
Sources: