cd /news/artificial-intelligence/on-measuring-semantic-preservation-i… · home topics artificial-intelligence article
[ARTICLE · art-96284] src=arxiv.org ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

On Measuring Semantic Preservation in Legal Ontology Learning

A new arXiv paper (2608.12326v1) proposes an evaluation methodology that measures semantic loss in ontology learning by comparing LLM task performance on source documents versus transformed representations, and demonstrates it on legal merger agreement analysis across six language models and three ontology learning methods. The results reveal systematic semantic loss that varies significantly with reasoning complexity and model-method interactions, providing guidance for selecting optimal configurations in legal knowledge systems.

read1 min views1 publishedAug 14, 2026

arXiv:2608.12326v1 Announce Type: new Abstract: Ontology learning transforms unstructured text into structured representations for automated reasoning. Yet structuring information risks losing it, and current evaluation methodologies cannot detect such loss, focusing on structural correctness while failing to measure whether meaning survives transformation. We propose an evaluation methodology that addresses this: comparing LLM task performance on source documents against performance on transformed representations, with the difference quantifying semantic loss. We demonstrate this approach on legal merger agreement analysis, a domain chosen for its complex language and precise semantic requirements, comparing direct LLM application against three ontology learning methods across six language models. The results reveal systematic semantic loss with significant variation based on reasoning complexity and model-method interactions. Our contributions are: (1) an evaluation framework for measuring semantic preservation in ontology learning, and (2) empirical evidence that semantic loss varies dramatically with model-method pairing, providing guidance for selecting optimal configurations in legal knowledge systems.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @arxiv 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/on-measuring-semanti…] indexed:0 read:1min 2026-08-14 ·