Science Journalism
Science journalism is evolving rapidly, leveraging artificial intelligence to improve the accessibility and efficiency of scientific communication. Current research focuses on developing and evaluating large language models (LLMs) for tasks such as summarizing scientific papers, generating lay summaries, and creating figures, often employing techniques like mixture-of-experts and retrieval-augmented generation. This work aims to enhance public understanding of science, improve the efficiency of scientific writing and figure creation, and address challenges in evaluating and ensuring the reliability of AI-driven scientific outputs.
Papers
Promoting AI Equity in Science: Generalized Domain Prompt Learning for Accessible VLM Research
Qinglong Cao, Yuntian Chen, Lu Lu, Hao Sun, Zhenzhong Zeng, Xiaokang Yang, Dongxiao Zhang
Computational Thought Experiments for a More Rigorous Philosophy and Science of the Mind
Iris Oved, Nikhil Krishnaswamy, James Pustejovsky, Joshua Hartshorne
A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students' Formative Assessment Responses in Science
Clayton Cohn, Nicole Hutchins, Tuan Le, Gautam Biswas
Science based AI model certification for untrained operational environments with application in traffic state estimation
Daryl Mupupuni, Anupama Guntu, Liang Hong, Kamrul Hasan, Leehyun Keel