# A Task-Centric Ontology and Deterministic Domain Rules as a Verifiable Core for AI-Assisted Chemistry Problem Solving

arXiv: https://arxiv.org/abs/2608.26164 · HTML: https://mlsanity.com/paper/2608.26164/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 25 references that are in the map.
- First posted on arXiv 12 Jul 2026.

## Builds on (most cited first, 10 of 10)

- [SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models](https://mlsanity.com/paper/2307.10635/) (2023)
- [What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks](https://mlsanity.com/paper/2305.18365/) (2023)
- [Neuro-Symbolic AI in 2024: A Systematic Review](https://mlsanity.com/paper/2501.05435/) (2025)
- [Are large language models superhuman chemists?](https://mlsanity.com/paper/2404.01475/) (2024)
- [Towards Cognitive AI Systems: a Survey and Prospective on Neuro-Symbolic AI](https://mlsanity.com/paper/2401.01040/) (2024)
- [QCBench: Evaluating Large Language Models on Domain-Specific Quantitative Chemistry](https://mlsanity.com/paper/2508.01670/) (2025)
- [A RAG Approach for Generating Competency Questions in Ontology Engineering](https://mlsanity.com/paper/2409.08820/) (2024)
- [KnowTD-An Actionable Knowledge Representation System for Thermodynamics](https://mlsanity.com/paper/2407.17169/) (2024)
- [Using Large Language Models for Solving Thermodynamic Problems](https://mlsanity.com/paper/2502.05195/) (2025)
- [Ontology-Guided Neuro-Symbolic Inference: Grounding Language Models with Mathematical Domain Knowledge](https://mlsanity.com/paper/2602.17826/) (2026)

## Abstract (arXiv)

Large language models can interpret natural-language chemistry questions, but their internal reasoning is difficult to inspect, constrain, and validate. This paper presents ChemOntoRule, a proof-of-concept symbolic core for AI-assisted school-level chemistry problem solving. The central design choice is task-centric ontology engineering: the ontology is constructed around the concepts, properties, relations, and executable procedures required by a defined collection of chemistry problems, rather than as a universal representation of chemistry. The implemented artifact combines a lightweight ontology serialized in JSON and RDF/Turtle with deterministic Python rules for electronic structure, periodic trends, oxidation states, oxide and hydride behavior, and related school-level reasoning patterns. A separate expert-coded fallback handles problem families not yet represented by general rules. The system was examined on 300 human-authored and manually validated chemistry problems. The complete system matched 296 of 300 reference answers (98.67%). The ontology-driven rule subset covered 269 problems and matched 266 references (98.88%); 31 problems were handled by task-specific expert-coded fallbacks, with 30 matches. Because the same collection informed ontology construction and evaluation, these results measure implemented coverage and internal consistency, not independent generalization. We analyze the four mismatches, distinguish structural validation from chemical correctness, and define a future architecture in which a language model acts primarily as a translator from user language into a normalized ontological task frame. Token efficiency is presented as a testable hypothesis for future controlled studies, not as a result of the current work.