Reproduce “Large Language Models Extend Known Research But Do Not Create New Research Directions” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Zhihua Liu, Kurt Butler, Damian Machlanski, Danilo Bueno, Sotirios A. Tsaftaris
The authors compare LLM-generated research hypotheses with published papers to assess distance from existing work and whether ideas extend beyond established research directions. They embed papers and hypotheses, then measure nearest-paper distance and orthogonal novelty score (ONS), an embedding-space proxy for direction. Generated hypotheses lie farther from papers, but median ONS is 15–23% lower; ONS does not establish originality.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.