按年被提到
20262026 · 2 次2026
大模型与语言模型›大模型推理与思维链·arXiv:2602.17826 · cs.AI

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

Marcelo Labre · 2026
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2026-02-26 · 最近 2026-03-23
2不同的人
2活跃月份
2讨论串
0被引(OpenAlex)
arXiv 摘要(候选层不写导读)

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.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)
讨论串评论marcelolabre · 2026-03

“Hi HN, Standard RAG retrieves semantic noise when confronted the logic of specialist domains like maths. I wanted to see if we could treat language models more like compilers by anchoring them to a structural ground truth. I built a neuro-symbolic pipeline that grounds smaller models (<9B parameters, like Gemma2 and Qwen2.5-Math) in the OpenMath ontolog…”

OpenMath: Ontology-Guided Neuro-Symbolic Inference原评论 ↗
被提交为 story · 2 次