Empowering scientific discovery with explainable small domain-specific and large language models
Guardat en:
| Publicat a: | The Artificial Intelligence Review vol. 58, no. 12 (Dec 2025), p. 371 |
|---|---|
| Autor principal: | |
| Altres autors: | , , , , , , |
| Publicat: |
Springer Nature B.V.
|
| Matèries: | |
| Accés en línia: | Citation/Abstract Full Text Full Text - PDF |
| Etiquetes: |
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3258735895 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 0269-2821 | ||
| 022 | |a 1573-7462 | ||
| 024 | 7 | |a 10.1007/s10462-025-11365-w |2 doi | |
| 035 | |a 3258735895 | ||
| 045 | 2 | |b d20251201 |b d20251231 | |
| 084 | |a 68693 |2 nlm | ||
| 100 | 1 | |a Yu, Hengjie |u Westlake University, School of Engineering, Hangzhou, China (GRID:grid.494629.4) (ISNI:0000 0004 8008 9315); Westlake Institute for Advanced Study, Institute of Advanced Technology, Hangzhou, China (GRID:grid.511490.8) | |
| 245 | 1 | |a Empowering scientific discovery with explainable small domain-specific and large language models | |
| 260 | |b Springer Nature B.V. |c Dec 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a As artificial intelligence (AI) increasingly integrates into scientific research, explainability has become a cornerstone for ensuring reliability and innovation in discovery processes. This review offers a forward-looking integration of explainable AI (XAI)-based research paradigms, encompassing small domain-specific models, large language models (LLMs), and agent-based large-small model collaboration. For domain-specific models, we introduce a knowledge-oriented taxonomy categorizing methods into knowledge-agnostic, knowledge-based, knowledge-infused, and knowledge-verified approaches, emphasizing the balance between domain knowledge and innovative insights. For LLMs, we examine three strategies for integrating domain knowledge—prompt engineering, retrieval-augmented generation, and supervised fine-tuning—along with advances in explainability, including local, global, and conversation-based explanations. We also envision future agent-based model collaborations within automated laboratories, stressing the need for context-aware explanations tailored to research goals. Additionally, we discuss the unique characteristics and limitations of both explainable small domain-specific models and LLMs in the realm of scientific discovery. Finally, we highlight methodological challenges, potential pitfalls, and the necessity of rigorous validation to ensure XAI’s transformative role in accelerating scientific discovery and reshaping research paradigms. | |
| 653 | |a Problem solving | ||
| 653 | |a Reliability | ||
| 653 | |a Knowledge | ||
| 653 | |a Classification | ||
| 653 | |a Discovery | ||
| 653 | |a Collaboration | ||
| 653 | |a Research | ||
| 653 | |a Methodological problems | ||
| 653 | |a Models | ||
| 653 | |a Taxonomy | ||
| 653 | |a Adoption of innovations | ||
| 653 | |a Prompt engineering | ||
| 653 | |a Laboratories | ||
| 653 | |a Artificial intelligence | ||
| 653 | |a Validity | ||
| 653 | |a Hypotheses | ||
| 653 | |a Innovations | ||
| 653 | |a Medical research | ||
| 653 | |a Paradigms | ||
| 653 | |a Global local relationship | ||
| 653 | |a Agent-based models | ||
| 653 | |a Scientists | ||
| 653 | |a Agnosticism | ||
| 653 | |a Retrieval | ||
| 653 | |a Knowledge management | ||
| 653 | |a Researchers | ||
| 653 | |a Automation | ||
| 653 | |a Explainable artificial intelligence | ||
| 653 | |a Large language models | ||
| 653 | |a Empowerment | ||
| 653 | |a Language modeling | ||
| 700 | 1 | |a Wang, Yizhi |u Westlake University, School of Engineering, Hangzhou, China (GRID:grid.494629.4) (ISNI:0000 0004 8008 9315) | |
| 700 | 1 | |a Cheng, Tao |u University College London, SpaceTimeLab, Department of Civil, Environmental and Geomatic Engineering, London, UK (GRID:grid.83440.3b) (ISNI:0000 0001 2190 1201) | |
| 700 | 1 | |a Yan, Yan |u University College Dublin, Centre for BioNano Interactions, School of Chemistry, Dublin 4, Ireland (GRID:grid.7886.1) (ISNI:0000 0001 0768 2743); UCD Conway Institute of Biomolecular and Biomedical Research, University College Dublin, School of Biomolecular and Biomedical Science, Dublin 4, Ireland (GRID:grid.7886.1) (ISNI:0000 0001 0768 2743) | |
| 700 | 1 | |a Dawson, Kenneth A. |u University College Dublin, Centre for BioNano Interactions, School of Chemistry, Dublin 4, Ireland (GRID:grid.7886.1) (ISNI:0000 0001 0768 2743) | |
| 700 | 1 | |a Li, Sam F. Y. |u National University of Singapore, Department of Chemistry, Singapore, Singapore (GRID:grid.428397.3) (ISNI:0000 0004 0385 0924) | |
| 700 | 1 | |a Zheng, Yefeng |u Westlake University, School of Engineering, Hangzhou, China (GRID:grid.494629.4) (ISNI:0000 0004 8008 9315); Westlake Institute for Advanced Study, Institute of Advanced Technology, Hangzhou, China (GRID:grid.511490.8) | |
| 700 | 1 | |a Jin, Yaochu |u Westlake University, School of Engineering, Hangzhou, China (GRID:grid.494629.4) (ISNI:0000 0004 8008 9315); Westlake Institute for Advanced Study, Institute of Advanced Technology, Hangzhou, China (GRID:grid.511490.8) | |
| 773 | 0 | |t The Artificial Intelligence Review |g vol. 58, no. 12 (Dec 2025), p. 371 | |
| 786 | 0 | |d ProQuest |t ABI/INFORM Global | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3258735895/abstract/embedded/Q8Z64E4HU3OH5N8U?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text |u https://www.proquest.com/docview/3258735895/fulltext/embedded/Q8Z64E4HU3OH5N8U?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3258735895/fulltextPDF/embedded/Q8Z64E4HU3OH5N8U?source=fedsrch |