We investigate whether large language models can perform the creative hypothesis generation that human researchers regularly do.While the error rate is high,generative AI seems to be able to effectively structure vast...We investigate whether large language models can perform the creative hypothesis generation that human researchers regularly do.While the error rate is high,generative AI seems to be able to effectively structure vast amounts of scientific knowledge and provide interesting and testable hypotheses.The future scientific enterprise may include synergistic efforts with a swarm of“hypothesis machines”,challenged by automated experimentation and adversarial peer reviews.展开更多
基金supported by a grant from the National Research Foundation of Korea(NRF)funded by the Korean government,Ministry of Science and ICT(MSIT)(No.2021R1A6A3A01086766)。
文摘We investigate whether large language models can perform the creative hypothesis generation that human researchers regularly do.While the error rate is high,generative AI seems to be able to effectively structure vast amounts of scientific knowledge and provide interesting and testable hypotheses.The future scientific enterprise may include synergistic efforts with a swarm of“hypothesis machines”,challenged by automated experimentation and adversarial peer reviews.
