This research introduces a novel framework that combines computational data with domain knowledge extracted by LLMs to accelerate high-entropy alloy discovery.

• Leverages large language models to distill knowledge from scientific literature
• Uses evidence theory to systematically fuse multiple knowledge sources
• Prioritizes promising material compositions in a vast design space
• Demonstrates superior performance compared to single-knowledge approaches

This approach significantly enhances materials engineering by reducing experimental costs and time while improving prediction accuracy for new alloy development, demonstrating a practical application of AI in advanced materials research.

Synergistic Fusion of Multi-Source Knowledge via Evidence Theory for High-Entropy Alloy Discovery