EMNLP Findings2025
polyBART: A Chemical Linguist for Polymer Property Prediction and Generative Design
Anagha Savit, Harikrishna Sahu, Shivank Shukla, Wei Xiong, Rampi Ramprasad
Abstract
Designing polymers for targeted applications and accurately predicting their properties is a key challenge in materials science owing to the vast and complex polymer chemical space. While molecular language models have proven effective in solving analogous problems for molecular discovery, similar advancements for polymers are limited. To address this gap, we propose polyBART, a language model-driven polymer discovery capability that enables rapid and accurate exploration of the polymer design space. Central to our approach is Pseudopolymer SELFIES (PSELFIES), a novel representation that allows for the transfer of molecular language models to the polymer space. polyBART is, to the best of our knowledge, the first language model capable of bidirectional translation between polymer structures and properties, achieving state-of-the-art results in property prediction and design of novel polymers for electrostatic energy storage. Further, polyBART is validated through a combination of both computational and laboratory experiments. We report what we believe is the first successful synthesis and validation of a polymer designed by a language model, predicted to exhibit high thermal degradation temperature and confirmed by our laboratory measurements. Our work presents a generalizable strategy for adapting molecular language models to the polymer space and introduces a polymer foundation model, advancing generative polymer design that may be adapted for a variety of applications.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on7
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Deberta: decoding-Enhanced Bert with Disentangled AttentionPengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu ChenICLR 2021 · 3,729 citations
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
- Fine-Tuned Language Models Generate Stable Inorganic Materials as TextNate Gruver, Anuroop Sriram, Andrea Madotto, Andrew Gordon Wilson et al.ICLR 2024 · 120 citations
- Translation between Molecules and Natural LanguageCarl Edwards, Tuan Manh Lai, Kevin Ros, Garrett Honke et al.EMNLP 2022 · 112 citations
Related papers
- How to Make Large Language Models Generate 100% Valid Molecules?Wen Tao, Jing Tang, Alvin Chan, Bryan Hooi et al.EMNLP 2025
- Representing Molecules as Random Walks Over Interpretable GrammarsMichael Sun, Minghao Guo, Weize Yuan, Veronika Thost et al.ICML 2024 · 6 citations
- PolyReal: A Benchmark for Real-World Polymer Science WorkflowsWanhao Liu, Weida Wang, Jiaqing Xie, Suorong Yang, Jue Wang, Benteng Chen, Guangtao Mei, Zonglin Yang, Shufei Zhang, Yuchun Mo, Lang Cheng, Jin Zeng, Houqiang Li, Wanli Ouyang, Yuqiang LiCVPR Findings 2026 · 3 citations
- NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule GenerationZhiyuan Liu, Yanchen Luo, Han Huang, Enzhi Zhang et al.ICLR 2025
- MolTailor: Tailoring Chemical Molecular Representation to Specific Tasks via Text PromptsHaoqiang Guo, Sendong Zhao, Haochun Wang, Yanrui Du et al.AAAI 2024 · 17 citations
