Buchumschlag

Empowering scientific discovery with explainable small domain-specific and large language models

Gespeichert in:
Veröffentlicht in:The Artificial Intelligence Review vol. 58, no. 12 (Dec 2025), p. 371
1. Verfasser: Yu, Hengjie
Weitere Verfasser: Wang, Yizhi, Cheng, Tao, Yan, Yan, Dawson, Kenneth A., Li, Sam F. Y., Zheng, Yefeng, Jin, Yaochu
Veröffentlicht:
Springer Nature B.V.
Schlagworte:
Problem solving
Reliability
Knowledge
Classification
Discovery
Collaboration
Research
Methodological problems
Models
Taxonomy
Adoption of innovations
Prompt engineering
Laboratories
Artificial intelligence
Validity
Hypotheses
Innovations
Medical research
Paradigms
Global local relationship
Agent-based models
Scientists
Agnosticism
Retrieval
Knowledge management
Researchers
Automation
Explainable artificial intelligence
Large language models
Empowerment
Language modeling
Online-Zugang:Citation/Abstract
Full Text
Full Text - PDF
Tags: Tag hinzufügen
Keine Tags, Fügen Sie das erste Tag hinzu!
Abstract: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.
ISSN:0269-2821
1573-7462
DOI:10.1007/s10462-025-11365-w
Quelle:ABI/INFORM Global