Kehan Guo
Papers
1
Total Citations
4
H-Index
1
About
Kehan Guo is a rising researcher at the forefront of AI safety and human-computer interaction, with a focused expertise in evaluating and mitigating risks posed by large language models (LLMs) in high-stakes environments. Their most-cited work, "Benchmarking large language models on safety risks in scientific laboratories" (2026), has already garnered 4 citations, signaling early impact in a critical niche. Guo’s major contribution lies in systematically assessing how LLMs might inadvertently cause harm in laboratory settings—such as generating unsafe protocols or misinterpreting safety data—thereby bridging the gap between AI capabilities and real-world operational safety. This research is pivotal for institutions adopting AI tools in research, as it provides a framework for pre-deployment risk analysis. Guo’s work not only advances technical benchmarks but also informs policy discussions on responsible AI deployment in scientific environments. As a young scholar, their ability to address emerging safety challenges with rigorous, actionable insights marks them as a key voice in the evolving dialogue on trustworthy AI, making their research essential reading for students and professionals navigating the intersection of AI and laboratory safety.
Research Focus
Key Achievements
Top Papers
- 1