betaFeedback

WorksPhysics and Astronomy

MolReps: Taking SELFIES, Making SMILES, Teaching LLMs

Abstract

The same molecule can be expressed in multiple, syntactically distinct representations, yet it remains unclear whether large language models (LLMs) can recognize and relate these equivalent encodings. We introduce MolReps, a pipeline that generates 9,600 question-answer pairs across ten representations for conversion, normalization, and 2D structure recognition. Post-training on MolReps improves text-only and multimodal models, MolQwen3-4B-Instruct (MQ3-4B-I) and MolQwen3-VL-4B-Instruct (MQ3-VL-4B-I), from 4.01%4.01\% to 75.13%75.13\% and from 7.11%7.11\% to 73.14%73.14\% (InChIKey match) on the molecule-overlap test set, respectively. On the molecule-disjoint test set, post-training increased validity from 20.35%20.35\% to 58.12%58.12\% for MQ3-4B-I and from 17.19%17.19\% to 59.34%59.34\% for MQ3-VL-4B-I. However, InChIKey match remained low, decreasing from 3.86%3.86\% to 3.09%3.09\% and from 6.44%6.44\% to 2.29%2.29\%, respectively. Furthermore, the resulting models achieve a relative 27.84%27.84\% improvement in average over their base model on MolRepBench, a comprehensive benchmark for evaluating molecular property prediction. These results show the effectiveness of targeted post-training for enhancing molecular representation understanding and its potential to improve downstream molecular tasks.

Paper details

vlnc:W_kr5hgvfg
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
arXiv nonexclusive license
Usage

views · 0

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Physics and Astronomy

Not recorded for this paper

View statement
Looking for related papers…