Knowledge Graphs as a source of trust for LLM-powered enterprise question answering
Generative AI provides an innovative and exciting way to manage knowledge and data at any scale; for small projects, at the enterprise level, and even at a world wide web scale. It is tempting to think that Generative AI has made other knowledge-based technologies obsolete; that anything we wanted t...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-05-01
|
| Series: | Web Semantics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1570826824000441 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832573195387928576 |
|---|---|
| author | Juan Sequeda Dean Allemang Bryon Jacob |
| author_facet | Juan Sequeda Dean Allemang Bryon Jacob |
| author_sort | Juan Sequeda |
| collection | DOAJ |
| description | Generative AI provides an innovative and exciting way to manage knowledge and data at any scale; for small projects, at the enterprise level, and even at a world wide web scale. It is tempting to think that Generative AI has made other knowledge-based technologies obsolete; that anything we wanted to do with knowledge-based systems, Knowledge Graphs or even expert systems can instead be done with Generative AI. Our position is counter to that conclusion.Our practical experience on implementing enterprise question answering systems using Generative AI has shown that Knowledge Graphs support this infrastructure in multiple ways: they provide a formal framework to evaluate the validity of a query generated by an LLM, serve as a foundation for explaining results, and offer access to governed and trusted data. In this position paper, we share our experience, present industry needs, and outline the opportunities for future research contributions. |
| format | Article |
| id | doaj-art-1a4becc1845c4fddb561a3d6fbc75efd |
| institution | Kabale University |
| issn | 1570-8268 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Web Semantics |
| spelling | doaj-art-1a4becc1845c4fddb561a3d6fbc75efd2025-02-02T05:26:58ZengElsevierWeb Semantics1570-82682025-05-0185100858Knowledge Graphs as a source of trust for LLM-powered enterprise question answeringJuan Sequeda0Dean Allemang1Bryon Jacob2Corresponding author.; data.world AI Lab, Austin, TX, USAdata.world AI Lab, Austin, TX, USAdata.world AI Lab, Austin, TX, USAGenerative AI provides an innovative and exciting way to manage knowledge and data at any scale; for small projects, at the enterprise level, and even at a world wide web scale. It is tempting to think that Generative AI has made other knowledge-based technologies obsolete; that anything we wanted to do with knowledge-based systems, Knowledge Graphs or even expert systems can instead be done with Generative AI. Our position is counter to that conclusion.Our practical experience on implementing enterprise question answering systems using Generative AI has shown that Knowledge Graphs support this infrastructure in multiple ways: they provide a formal framework to evaluate the validity of a query generated by an LLM, serve as a foundation for explaining results, and offer access to governed and trusted data. In this position paper, we share our experience, present industry needs, and outline the opportunities for future research contributions.http://www.sciencedirect.com/science/article/pii/S1570826824000441Knowledge GraphLLMLarge Language ModelGenerative AIQuestion answeringKnowledge engineering |
| spellingShingle | Juan Sequeda Dean Allemang Bryon Jacob Knowledge Graphs as a source of trust for LLM-powered enterprise question answering Web Semantics Knowledge Graph LLM Large Language Model Generative AI Question answering Knowledge engineering |
| title | Knowledge Graphs as a source of trust for LLM-powered enterprise question answering |
| title_full | Knowledge Graphs as a source of trust for LLM-powered enterprise question answering |
| title_fullStr | Knowledge Graphs as a source of trust for LLM-powered enterprise question answering |
| title_full_unstemmed | Knowledge Graphs as a source of trust for LLM-powered enterprise question answering |
| title_short | Knowledge Graphs as a source of trust for LLM-powered enterprise question answering |
| title_sort | knowledge graphs as a source of trust for llm powered enterprise question answering |
| topic | Knowledge Graph LLM Large Language Model Generative AI Question answering Knowledge engineering |
| url | http://www.sciencedirect.com/science/article/pii/S1570826824000441 |
| work_keys_str_mv | AT juansequeda knowledgegraphsasasourceoftrustforllmpoweredenterprisequestionanswering AT deanallemang knowledgegraphsasasourceoftrustforllmpoweredenterprisequestionanswering AT bryonjacob knowledgegraphsasasourceoftrustforllmpoweredenterprisequestionanswering |