Tom Soru
@mommi84.bsky.social
Neuro-Symbolic is the way. 🧠🔗
Associate Consultant @ Ortecha
Founder & Researcher @ Liber AI
Lead Mentor @ DBpedia
Musician
🇪🇺🇮🇹🇩🇪🇬🇧
Associate Consultant @ Ortecha
Founder & Researcher @ Liber AI
Lead Mentor @ DBpedia
Musician
🇪🇺🇮🇹🇩🇪🇬🇧
Can AI drive the construction of Enterprise ontologies?
We propose OntoEKG, an LLM-based pipeline designed to accelerate the generation of domain-specific ontologies from unstructured Enterprise data.
To appear in: 20th IEEE International Conference on Semantic Computing.
arxiv.org/abs/2602.01276
We propose OntoEKG, an LLM-based pipeline designed to accelerate the generation of domain-specific ontologies from unstructured Enterprise data.
To appear in: 20th IEEE International Conference on Semantic Computing.
arxiv.org/abs/2602.01276
February 13, 2026 at 7:43 PM
Can AI drive the construction of Enterprise ontologies?
We propose OntoEKG, an LLM-based pipeline designed to accelerate the generation of domain-specific ontologies from unstructured Enterprise data.
To appear in: 20th IEEE International Conference on Semantic Computing.
arxiv.org/abs/2602.01276
We propose OntoEKG, an LLM-based pipeline designed to accelerate the generation of domain-specific ontologies from unstructured Enterprise data.
To appear in: 20th IEEE International Conference on Semantic Computing.
arxiv.org/abs/2602.01276
Reminder: Large Language Models may have hidden agendas. And there is no on-off switch in neural models. Neurosymbolic integration is necessary for human safety.
Image from twitter.com/AISafetyMemes
Image from twitter.com/AISafetyMemes
December 17, 2025 at 12:37 PM
Reminder: Large Language Models may have hidden agendas. And there is no on-off switch in neural models. Neurosymbolic integration is necessary for human safety.
Image from twitter.com/AISafetyMemes
Image from twitter.com/AISafetyMemes
The GPT-5 Thinking model spectacularly fails to apply Ockham's razor. Pattern recognition isn't enough for AGI. Why is it so hard for OpenAI to admit we need neurosymbolic approaches?
September 7, 2025 at 1:22 PM
The GPT-5 Thinking model spectacularly fails to apply Ockham's razor. Pattern recognition isn't enough for AGI. Why is it so hard for OpenAI to admit we need neurosymbolic approaches?
Going to present our latest work 'Anticipating the Future with Large Language Models' at the 19th IEEE International Conference on Semantic Computing today.
Pre-print: arxiv.org/abs/2501.04880
Pre-print: arxiv.org/abs/2501.04880
February 5, 2025 at 1:48 PM
Going to present our latest work 'Anticipating the Future with Large Language Models' at the 19th IEEE International Conference on Semantic Computing today.
Pre-print: arxiv.org/abs/2501.04880
Pre-print: arxiv.org/abs/2501.04880