Paper recorded by Signals 4 on 2026-09-04 in cs.AI. Abstract reproduced from arXiv; link to the original below.
Published 2026-09-04 on arXiv · recorded by Signals 4 on 2026-09-07
Category: cs.AI · 人工智能 · first seen 2026-09-07
Large language models (LLMs) are increasingly evaluated on molecular property benchmarks, but accuracy cannot distinguish a model that predicts a property from one that retrieves a published number. We audit 22 frontier models on 12 regression benchmarks for verbatim retrieval and find that it is widespread but relatively benchmark-specific: on five datasets more than $50\%$ of the LLMs show verba