Do General NLP Embeddings Capture Ontological Reasoning?
cs.CL, cs.AI
Submitted: 2026-08-31
Updated: 2026-08-31
Comments: 7 pages, 3 figures. Accepted as a short paper at CIKM 2026
Code: https://github.com/sciknoworg/AVA
License: http://creativecommons.org/licenses/by/4.0/
The gist: General-purpose NLP embedding models perform well on linguistic tasks, but their ability to capture symbolic ontological structure remains unclear.
Terminology
Abstract
General-purpose NLP embedding models perform well on linguistic tasks, but their ability to capture symbolic ontological structure remains unclear. We introduce AVA, a systematic framework for evaluating whether embeddings distinguish logic-sensitive relational semantics in ontologies and knowledge graphs. AVA comprises 171,007 contrastive triplets derived from 163 heterogeneous ontologies using hierarchy inversion, relation substitution, and disjointness injection. Each triplet contains an ontology statement, a semantically equivalent paraphrase, and a logic-sensitive hard negative with contradictory relational meaning. We evaluate more than 25 state-of-the-art embedding models and find substantial limitations: the best model achieves only 0.739 triplet accuracy, while hard negative accuracy falls to 0.135. Fine-tuning improves discrimination by a large margin but transfers poorly to downstream Semantic Web tasks, including taxonomy discovery and ontology alignment. Further analysis suggests that improvements stem partly from perturbation-specific pattern recognition rather than robust ontological understanding. These findings reveal a persistent gap between linguistic representation learning and ontology-level discrimination, challenging the assumption that strong NLP benchmark performance translates to Semantic Web competence.
Sources
- LLM-empowered knowledge graph construction: A survey
- OntoLearner: A Modular Python Library for Ontology Learning with Large Language Models
- Advances and Challenges in Semantic Textual Similarity: A Comprehensive Survey
- Towards Efficient LLM-aware Heterogeneous Graph Learning
- Towards General Text Embeddings with Multi-stage Contrastive Learning
- Efficient Estimation of Word Representations in Vector Space
- Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning
- RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
- Text Embeddings by Weakly-Supervised Contrastive Pre-training
- KG-BERT: BERT for Knowledge Graph Completion
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering