Tacit Knowledge Extraction via Logic Augmented Generation and Active Inference
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915992572002304 |
|---|---|
| author | Lamazzi, Lorenzo Gangemi, Aldo Giberti, Alessio Nuzzolese, Andrea Giovanni Rocca, Vittorio Andrea Torta, Mattia Poggi, Francesco |
| author_facet | Lamazzi, Lorenzo Gangemi, Aldo Giberti, Alessio Nuzzolese, Andrea Giovanni Rocca, Vittorio Andrea Torta, Mattia Poggi, Francesco |
| contents | Tacit knowledge plays a central role in human expertise, yet it remains difficult to capture, formalize, and reuse in machine-interpretable form. This challenge is especially relevant in procedural domains, where successful execution depends not only on explicit instructions, but also on implicit assumptions, contextual constraints, embodied skills, and experience-based judgments rarely documented. As a result, current knowledge engineering pipelines struggle to transform tacit and process-centric knowledge into formally specified, machine-interpretable representations that can be queried, validated, reasoned over, and reused. In this paper, we introduce a neuro-symbolic framework that combines Logic-Augmented Generation and an Active-Inference-inspired approach for ontology-grounded Knowledge Graph construction. We evaluate the approach in a knowledge transfer case study in manufacturing, using assembly-like repair procedures from instructional videos as a reproducible proxy domain. Results show that the proposed solution improves completeness and semantic quality, advancing neuro-symbolic knowledge engineering for industrial domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_07639 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Tacit Knowledge Extraction via Logic Augmented Generation and Active Inference Lamazzi, Lorenzo Gangemi, Aldo Giberti, Alessio Nuzzolese, Andrea Giovanni Rocca, Vittorio Andrea Torta, Mattia Poggi, Francesco Artificial Intelligence Tacit knowledge plays a central role in human expertise, yet it remains difficult to capture, formalize, and reuse in machine-interpretable form. This challenge is especially relevant in procedural domains, where successful execution depends not only on explicit instructions, but also on implicit assumptions, contextual constraints, embodied skills, and experience-based judgments rarely documented. As a result, current knowledge engineering pipelines struggle to transform tacit and process-centric knowledge into formally specified, machine-interpretable representations that can be queried, validated, reasoned over, and reused. In this paper, we introduce a neuro-symbolic framework that combines Logic-Augmented Generation and an Active-Inference-inspired approach for ontology-grounded Knowledge Graph construction. We evaluate the approach in a knowledge transfer case study in manufacturing, using assembly-like repair procedures from instructional videos as a reproducible proxy domain. Results show that the proposed solution improves completeness and semantic quality, advancing neuro-symbolic knowledge engineering for industrial domains. |
| title | Tacit Knowledge Extraction via Logic Augmented Generation and Active Inference |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2605.07639 |