Huashan Sun
Papers
1
Total Citations
14
H-Index
1
About
Huashan Sun is a leading researcher whose work centers on the fundamental capabilities and real-world applications of large language models (LLMs). Sun’s major contribution lies in systematically mapping how core LLM abilities—such as reasoning, knowledge retrieval, and in-context learning—drive success across diverse domains, from healthcare to software engineering. This foundational work, most notably the highly cited survey "Fundamental Capabilities and Applications of Large Language Models" (2025, 14 citations), clarifies which capabilities matter most for specific tasks, directly addressing a critical gap in LLM evaluation. By disentangling these relationships, Sun has provided a crucial framework for designing more targeted benchmarks and improving model transparency. This research has already shaped how practitioners assess LLM performance, moving beyond generic metrics to capability-driven analysis. Sun’s achievements include advancing the theoretical understanding of LLM behavior while offering practical guidance for deployment, making their work essential reading for anyone building or evaluating language AI systems.
Research Focus
Key Achievements
Top Papers
- 1Fundamental Capabilities and Applications of Large Language Models: A Survey14 citations · 2025