# MoleculeQA: A Dataset to Evaluate Factual Accuracy in Molecular Comprehension

Source: [MoleculeQA: A Dataset to Evaluate Factual Accuracy in Molecular Comprehension](<https://www.sota2.com/research/paper/68fa5f561e209131ce9e9079>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T19:13:45.935Z

Authors: Xingyu Lu, He Cao, Zijing Liu, Shengyuan Bai, Leqing Chen, Yuan Yao, Hai-Tao Zheng, Yu Li

Published: 2024-03-13T02:26:16.000Z

## Abstract

Large language models are playing an increasingly significant role in molecular research, yet existing models often generate erroneous information, posing challenges to accurate molecular comprehension. Traditional evaluation metrics for generated content fail to assess a model's accuracy in molecular understanding. To rectify the absence of factual evaluation, we present MoleculeQA, a novel question answering (QA) dataset which possesses 62K QA pairs over 23K molecules. Each QA pair, composed of a manual question, a positive option and three negative options, has consistent semantics with a molecular description from authoritative molecular corpus. MoleculeQA is not only the first benchmark for molecular factual bias evaluation but also the largest QA dataset for molecular research. A comprehensive evaluation on MoleculeQA for existing molecular LLMs exposes their deficiencies in specific areas and pinpoints several particularly crucial factors for molecular understanding.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2403.08192>)

[PDF](<https://arxiv.org/pdf/2403.08192.pdf>)
