Ai2 finds LLM novelty judges give unstable verdicts on research ideas
AIAi2 releases Old Ideas, Novel Problems, a study of how reliably LLMs judge the novelty of research ideas, along with a benchmark, data, and code. Across six LLM judges, changing a few prompt words shifted accuracy on AI-generated ideas by more than 50 percentage points.
AIWhy it matters.
The study shows that small prompt and setup changes can flip LLM novelty judgments, so readers evaluating AI-generated research ideas should check the judge setup.
Loading source posts…
Source details
Ai2 (Allen Institute for AI) · allenai.orgPublished · added here
Original title: Can we trust LLMs to judge whether a research idea is novel?