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.
Abstract (translated)
语言模型存在基本的局限性——幻觉、脆弱性和缺乏形式化基础——这些问题在需要可验证推理的高风险专业领域中尤为严重。我研究了正式领域的本体论是否可以通过检索增强生成来提高语言模型的可靠性。以数学为例，我实现了一个神经符号管道，利用OpenMath本体结合混合检索和交叉编码重排序技术，将相关定义注入到模型提示中。在MATH基准测试上使用三个开源模型进行评估后发现，在检索质量高的情况下，基于本体论的上下文可以改善性能；然而，不相关的上下文则会降低其表现——这既突显了神经符号方法的潜力也展示了面临的挑战。
URL
https://arxiv.org/abs/2602.17826
