arXiv AI September 2, 2026 By Hamed Babaei Giglou, Jennifer D'Souza, S\"oren Auer

Do General NLP Embeddings Capture Ontological Reasoning?

The paper introduces AVA, a framework that tests whether general NLP embeddings can differentiate logic-sensitive relational semantics in ontologies and knowledge graphs. AVA uses 171,007 contrastive triplets from 163 ontologies, each containing an ontology statement, a paraphrase, and a hard negative with contradictory meaning. Evaluation of over 25 embedding models shows significant limitations, with the best model achieving only 0.739 triplet accuracy and 0.135 for hard negatives; fine‑tuning helps but does not transfer well to downstream Semantic Web tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Hugging Face Trending Papers

Aug 31

Do General NLP Embeddings Capture Ontological Reasoning?

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 evaluat...

rag nlp fine-tuning benchmarks safety

arXiv Computation and Language

Sep 23

Semantic Abstraction for Natural Language Inference: a Methodological Framework for Discovering and Compensating Semantic Knowledge and Reasoning Gaps in Large Language Models

arXiv:2609.26610v1 Announce Type: new Abstract: Despite their outstanding performance on many NLP tasks, LLMs face serious challenges related to semantic abstraction. In this study, we are interested...

By David Torres-Moreno, Jorge Hermosillo-Valadez

llms agents nlp

arXiv AI

Jun 3

ReaLM: Residual Quantization Bridging Knowledge Graph Embeddings and Large Language Models

arXiv:2510. 09711v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have recently emerged as a powerful paradigm for Knowledge Graph Completion (KGC), offering strong reasoning and generalization capabilities beyond traditional embedding-based approaches.

By Wenbin Guo, Xin Wang, Jiaoyan Chen, Lingbing Guo, Zhao Li, Zirui Chen

llms rag nlp efficiency benchmarks

arXiv AI

Oct 2

LLM-Assisted Discovery of Typed Semantic Links for Ontology Network Construction

The paper presents an automated framework for building ontology networks by discovering typed semantic links between concepts across domains. It uses domain‑adapted DistilBERT embeddings, clustering to prune candidates, and GPT‑4o for generating interpretable relationships, reducing 800k raw pairs to 95k high‑quality candidates. Human validation on 429 links shows an 80.19% precision and 0.890 F1, outperforming five similarity‑based baselines and demonstrating the need for LLM reasoning in ontology link construction.

By Nouha Hayouni, Sheeba Samuel, Alsayed Algergawy

llms rag benchmarks

arXiv AI

Jun 30

Measuring Graph-to-Graph Semantic Similarity in Knowledge Graphs: An Empirical Evaluation of Knowledge Graph Embeddings

arXiv:2606. 29180v1 Announce Type: new Abstract: A Knowledge Graph (KG) represents facts as structured triples and is widely used to organize relational knowledge across diverse domains.

By Seungryeol Baek, Wooseok Sim, Hogun Park

rag

arXiv AI

Sep 10

Better Later Than Sooner: Neuro-Symbolic Knowledge Graph Construction via Ontology-grounded Post-extraction Correction

The paper introduces a neuro‑symbolic framework for constructing knowledge graphs (KGs) that are grounded in an ontology. It combines open‑domain extraction, embedding‑based canonicalization of types and predicates, and a post‑extraction LLM‑based correction step to fix ontology violations, thereby reducing token usage and improving KG consistency. The resulting KGs support symbolic querying, as evidenced by the prevalence of SPARQL graph patterns in the extracted data.

By Lorenzo Loconte, Timothy Hospedales, Cristina Cornelio

llms rag nlp data-engineering

One email a morning, machine-written

Related stories

Do General NLP Embeddings Capture Ontological Reasoning?

Semantic Abstraction for Natural Language Inference: a Methodological Framework for Discovering and Compensating Semantic Knowledge and Reasoning Gaps in Large Language Models

ReaLM: Residual Quantization Bridging Knowledge Graph Embeddings and Large Language Models

LLM-Assisted Discovery of Typed Semantic Links for Ontology Network Construction

Measuring Graph-to-Graph Semantic Similarity in Knowledge Graphs: An Empirical Evaluation of Knowledge Graph Embeddings

Better Later Than Sooner: Neuro-Symbolic Knowledge Graph Construction via Ontology-grounded Post-extraction Correction