English
Related papers

Related papers: Tokenization for Molecular Foundation Models

200 papers

Purpose: Large Language Models (LLMs) like GPT (Generative Pre-trained Transformer) from OpenAI and LLaMA (Large Language Model Meta AI) from Meta AI are increasingly recognized for their potential in the field of cheminformatics,…

Biomolecules · Quantitative Biology 2024-05-22 Shaghayegh Sadeghi , Alan Bui , Ali Forooghi , Jianguo Lu , Alioune Ngom

We introduce a new tokenizer for language models that minimizes the average tokens per character, thereby reducing the number of tokens needed to represent text during training and to generate text during inference. Our method, which we…

Computation and Language · Computer Science 2025-11-27 Dong Dong , Weijie Su

Tokenization is a fundamental preprocessing step in NLP, directly impacting large language models' (LLMs) ability to capture syntactic, morphosyntactic, and semantic structures. This paper introduces a novel framework for systematically…

Computation and Language · Computer Science 2025-07-22 M. Ali Bayram , Ali Arda Fincan , Ahmet Semih Gümüş , Sercan Karakaş , Banu Diri , Savaş Yıldırım

Tokenization plays a pivotal role in multilingual NLP. However, existing tokenizers are often skewed towards high-resource languages, limiting their effectiveness for linguistically diverse and morphologically rich languages such as those…

Computation and Language · Computer Science 2025-06-25 N J Karthika , Maharaj Brahma , Rohit Saluja , Ganesh Ramakrishnan , Maunendra Sankar Desarkar

Molecular representation learning is fundamental for many drug related applications. Most existing molecular pre-training models are limited in using single molecular modality, either SMILES or graph representation. To effectively leverage…

Machine Learning · Computer Science 2024-11-05 Shikun Feng , Lixin Yang , Yanwen Huang , Yuyan Ni , Weiying Ma , Yanyan Lan

Molecules are graphs, but large language models~(LLMs) are usually asked to reason about them through linear strings. The most popular molecular representation, SMILES, compresses atoms, bonds, branches and rings into a compact sequence in…

Biomolecules · Quantitative Biology 2026-05-19 Zhiyuan Yan , Chen Liu , Boxuan Zhao , Kaiqing Lin , Jixiang Zhao , Yimi Wang , Liuzhenghao Lv , Hao Li , Shanzhuo Zhang , Li Yuan , Fanyang Mo

Purely character-based language models (LMs) have been lagging in quality on large scale datasets, and current state-of-the-art LMs rely on word tokenization. It has been assumed that injecting the prior knowledge of a tokenizer into the…

Computation and Language · Computer Science 2019-08-28 Dokook Choe , Rami Al-Rfou , Mandy Guo , Heeyoung Lee , Noah Constant

Image tokenizers form the foundation of modern text-to-image generative models but are notoriously difficult to train. Furthermore, most existing text-to-image models rely on large-scale, high-quality private datasets, making them…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Dongwon Kim , Ju He , Qihang Yu , Chenglin Yang , Xiaohui Shen , Suha Kwak , Liang-Chieh Chen

Large language models (LLMs) are increasingly recognized as powerful tools for scientific discovery, particularly in molecular science. A fundamental requirement for these models is the ability to accurately understand molecular structures,…

Machine Learning · Computer Science 2025-05-23 Yunhui Jang , Jaehyung Kim , Sungsoo Ahn

Accurate molecular property prediction is central to drug discovery, catalysis, and process design, yet real-world applications are often limited by small datasets. Molecular foundation models provide a promising direction by learning…

Machine Learning · Computer Science 2026-04-21 Karim K. Ben Hicham , Jan G. Rittig , Martin Grohe , Alexander Mitsos

With the emergence of Transformer architectures and their powerful understanding of textual data, a new horizon has opened up to predict the molecular properties based on text description. While SMILES are the most common form of…

Chemical Physics · Physics 2023-10-11 Suryanarayanan Balaji , Rishikesh Magar , Yayati Jadhav , Amir Barati Farimani

The discovery of novel materials and functional molecules can help to solve some of society's most urgent challenges, ranging from efficient energy harvesting and storage to uncovering novel pharmaceutical drug candidates. Traditionally…

Machine Learning · Computer Science 2020-11-06 Mario Krenn , Florian Häse , AkshatKumar Nigam , Pascal Friederich , Alán Aspuru-Guzik

Although recent advances in quantum machine learning (QML) offer significant potential for enhancing generative models, particularly in molecular design, a large array of classical approaches still face challenges in achieving high fidelity…

Machine Learning · Computer Science 2025-08-29 Afrar Jahin , Yi Pan , Yingfeng Wang , Tianming Liu , Wei Zhang

Subword tokenization is an essential part of modern large language models (LLMs), yet its specific contributions to training efficiency and model performance remain poorly understood. In this work, we decouple the effects of subword…

Computation and Language · Computer Science 2026-05-15 Théo Gigant , Bowen Peng , Jeffrey Quesnelle

Models that accurately predict properties based on chemical structure are valuable tools in drug discovery. However, for many properties, public and private training sets are typically small, and it is difficult for the models to generalize…

Quantitative Methods · Quantitative Biology 2022-11-08 Oscar Méndez-Lucio , Christos Nicolaou , Berton Earnshaw

Molecular representation learning methods typically tokenize molecules as individual atoms or use rigid, rule-based fragment decompositions, limiting their ability to capture meaningful chemical substructure context. We introduce…

Machine Learning · Computer Science 2026-05-26 Ankur Samanta , Rohan Gupta , Aditi Misra , Christian McIntosh Clarke , Jayakumar Rajadas

Recently, Large Language Models (LLMs) have demonstrated great potential in natural language-driven molecule discovery. However, existing datasets and benchmarks for molecule-text alignment are predominantly built on one-to-one mappings,…

Computation and Language · Computer Science 2026-05-25 Jiatong Li , Junxian Li , Weida Wang , Yunqing Liu , Changmeng Zheng , Yatao Bian , Dongzhan Zhou , Xiao-yong Wei , Qing Li

This work investigates how effectively large language models (LLMs) and their tokenization schemes represent and generate Arabic root-pattern morphology, probing whether they capture genuine morphological structure or rely on surface…

Computation and Language · Computer Science 2026-03-18 Yara Alakeel , Chatrine Qwaider , Hanan Aldarmaki , Sawsan Alqahtani

Despite recent successes in language models, their ability to represent numbers is insufficient. Humans conceptualize numbers based on their magnitudes, effectively projecting them on a number line; whereas subword tokenization fails to…

Computation and Language · Computer Science 2023-10-11 Avijit Thawani , Jay Pujara , Ashwin Kalyan

Automatic n-gram based metrics such as ROUGE are widely used for evaluating generative tasks such as summarization. While these metrics are considered indicative (even if imperfect) of human evaluation for English, their suitability for…

Computation and Language · Computer Science 2025-07-14 Itai Mondshine , Tzuf Paz-Argaman , Reut Tsarfaty