#ai

Hmm llm showed some level of creativity when proposing research ideas in these experiments.

> we find LLM-generated ideas are judged as more novel (p < 0.05) than human expert ideas while being judged slightly weaker on feasibility.

[2409.04109] Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers
https://arxiv.org/abs/2409.04109

arXiv.org

Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study...

Recent advancements in large language models (LLMs) have sparked optimism about their potential to accelerate scientific discovery, with a growing number of works proposing research agents that...