Pith. sign in

REVIEW 13 cited by

Translation between Molecules and Natural Language

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2204.11817 v3 pith:MZTCQ2KR submitted 2022-04-25 cs.CL cs.AI

classification cs.CLcs.AI
keywords moleculemolt5textbflanguagemodelsmoleculescaptioningdata
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

We present $\textbf{MolT5}$ $-$ a self-supervised learning framework for pretraining models on a vast amount of unlabeled natural language text and molecule strings. $\textbf{MolT5}$ allows for new, useful, and challenging analogs of traditional vision-language tasks, such as molecule captioning and text-based de novo molecule generation (altogether: translation between molecules and language), which we explore for the first time. Since $\textbf{MolT5}$ pretrains models on single-modal data, it helps overcome the chemistry domain shortcoming of data scarcity. Furthermore, we consider several metrics, including a new cross-modal embedding-based metric, to evaluate the tasks of molecule captioning and text-based molecule generation. Our results show that $\textbf{MolT5}$-based models are able to generate outputs, both molecules and captions, which in many cases are high quality.

Discussion (0). Sign in to comment.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Atomistic Language Models Understand and Generate Materials

    cs.LG 2026-06 unverdicted novelty 7.0 of 10

    ALMs unify pretrained atomistic encoder, LLM, and denoising diffusion via continuous projectors and staged training to reach SOTA on text-conditioned crystal prediction and de novo generation.

  2. MoleCode unlocks structural intelligence in large language models

    q-bio.BM 2026-05 unverdicted novelty 7.0 of 10

    MoleCode is a training-free, LLM-native representation that makes molecular graphs with explicit atoms, bonds, and topology directly readable and editable in language models, improving structural tasks over implicit s...

  3. Back to Basics: Improving Molecular Understanding in LLMs via SMILES-Graph Translation

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Training LLMs first on bidirectional SMILES–graph conversion plus progressive CoT yields large structure-perception gains and better property prediction and molecular optimization.

  4. OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation

    cs.CL 2026-06 unverdicted novelty 6.0 of 10

    OPD-Evolver uses on-policy self-distillation in fast interaction and slow attribution loops to build agents with holistic memory competence, outperforming prior systems by up to 11.5% and allowing a 9B model to compet...

  5. Mol-Debate: Multi-Agent Debate Improves Structural Reasoning in Molecular Design

    cs.AI 2026-04 unverdicted novelty 6.0 of 10

    Mol-Debate applies multi-agent debate in an iterative loop with perspective orchestration to achieve state-of-the-art text-guided molecular design, scoring 59.82% exact match on ChEBI-20 and 50.52% weighted success on...

  6. IR-Agent: Expert-Inspired LLM Agents for Structure Elucidation from Infrared Spectra

    cs.AI 2025-08 unverdicted novelty 6.0 of 10

    IR-Agent is a multi-agent LLM framework that emulates expert IR spectral analysis procedures to improve molecular structure elucidation accuracy and adaptability.

  7. SciCore-Mol: Augmenting Large Language Models with Pluggable Molecular Cognition Modules

    cs.AI 2026-05 unverdicted novelty 5.0 of 10

    SciCore-Mol augments LLMs with three integrated modules for molecular perception, latent diffusion generation, and reaction reasoning, claiming an 8B open model competes with or exceeds proprietary systems on chemical tasks.

  8. NMIRacle: Multi-modal Generative Molecular Elucidation from IR and NMR Spectra

    physics.chem-ph 2025-12 conditional novelty 5.0 of 10

    NMIRacle generates molecular structures from combined raw IR and NMR spectra, improving Top-1 elucidation accuracy from 0.41 to 0.48 over the NMR2Struct baseline on the Alberts benchmark.

  9. An Encoder-Decoder Foundation Chemical Language Model for Generative Polymer Design

    cond-mat.mtrl-sci 2025-10 conditional novelty 5.0 of 10

    A T5-based polymer language model pre-trained on 100 million hypothetical polymers predicts thermal, electronic, and solubility properties and generates polymers conditioned on a target glass-transition temperature, w...

  10. HSA-Net: Hierarchical and Structure-Aware Framework for Efficient and Scalable Molecular Language Modeling

    cs.LG 2025-08 reject novelty 5.0 of 10

    HSA-Net improves molecular language modeling by adaptively switching between cross-attention and Mamba projectors across GNN layers and fusing the results with a sparse mixture-of-experts.

  11. CROP: Integrating Topological and Spatial Structures via Cross-View Prefixes for Molecular LLMs

    q-bio.QM 2025-08 conditional novelty 5.0 of 10

    Cross-view prefix resampling, guided by the LLM's SMILES encoding, lets a Galactica-based model exploit molecular graphs and images at low context cost, improving captioning, IUPAC naming, and property prediction.

  12. Adopting Reinforcement Learning with Verifiable Rewards for Molecular Generation

    cs.LG 2026-07 reject novelty 4.0 of 10

    LLMol fine-tunes an LLM on simplified SELFIES and uses GRPO with RDKit-derived rewards for targeted molecular generation, but its own benchmark tables contradict the claimed state-of-the-art performance.

  13. SmileyLlama: Modifying Large Language Models for Directed Chemical Space Exploration

    physics.chem-ph 2024-09 unverdicted novelty 4.0 of 10

    SmileyLlama is an LLM transformed via SFT and DPO to generate valid novel drug-like molecules with user-specified properties and optimized 3D conformations for high binding affinity.

Pith tools