LLMs are increasingly used to judge whether AI-generated research ideas are novel. But are they any good at it?
摘要
Ai2 发布一项评测，考察大语言模型判断 AI 生成科研想法是否新颖的能力，发现即便是前沿模型，对相似想法也会因被要求评估的方式不同而得出不同结论。相关代码已在 GitHub 的 allenai/novelty-eval 仓库公开。
摘要由模型根据原文撰写，以原文为准。
正文 · 原文
LLMs are increasingly used to judge whether AI-generated research ideas are novel. But are they any good at it?
Our new eval reveals even frontier LLMs can reach different conclusions about similar ideas depending on how they're asked to evaluate them. 🧵
来源：Ai2 · x.com
引用原文
allen_ai. LLMs are increasingly used to judge whether AI-generated research ideas are novel. But are they any good at it?[EB/OL]. (2026-10-28)[访问日期]. https://x.com/allen_ai/status/2115120549680521403.