[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-327639-105":59,"doc-detail-327639-en":122},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":115,"head_meta":117,"extra_data":119,"updated_unix":121},105,"en","back-to-basics-improving-molecular-understanding-in-llms-via-smiles-graph-translation","Back to Basics - Improving Molecular Understanding in LLMs via SMILES - Graph Translation","","Recent advances in molecular large language models show strong performance on molecular understanding and generation, but often lack reliable structural grounding. Existing methods conflict with the chemistry principle that structure determines function: despite downstream success, current molecular LLMs struggle with basic structure recognition and fail to capture molecular graphs from canonical SMILES. MolBasic addresses this with a structure-first framework using multi-level structure perception and bidirectional SMILES–Graph translation.",{"@graph":69,"@context":114},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/back-to-basics-improving-molecular-understanding-in-llms-via-smiles-graph-translation/327639/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/back-to-basics-improving-molecular-understanding-in-llms-via-smiles-graph-translation/327639.png","ImageObject",300,407,{"name":92,"@type":93},"Noah","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":24},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108],{"name":109,"@type":110,"acceptedAnswer":111},"How does MolBasic help models move from structure acquisition to higher-level reasoning?","Question",{"text":112,"@type":113},"It adds a progressive learning scheme with a standardized Chain-of-Thought (CoT) to guide learning from structural acquisition toward higher-level molecular reasoning.","Answer","https://schema.org",{"og:url":83,"og:type":116,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":118,"canonical":83},"index,follow",{"doc_id":120,"site_id":62},327639,1790884490,{"code":4,"msg":5,"data":123},{"doc_id":120,"user_id":124,"nickname":92,"user_avatar":125,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":126,"file_id":127,"file_url":128,"file_type":129,"file_size":130,"view_count":24,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":131,"language":132,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":133,"faqs":134,"seo_title":135,"seo_description":67,"update_tm":136,"read_time":137,"preview_page_count":4},8796095462418,"https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780","Back to Basics: Improving Molecular Understanding in LLMs via  \nSMILES–Graph Translation  \nWenda Wang  \nGaoling School of Artificial Intelligence  \nRenmin University of China Beijing, China [wangwenda87@ruc.edu.cn](wangwenda87@ruc.edu.cn)  \nJinjia Feng  \nGaoling School of Artificial Intelligence  \nRenmin University of China Beijing, China [jinjia_feng@ruc.edu.cn](jinjia_feng@ruc.edu.cn)  \nZhewei Wei  \nGaoling School of Artificial Intelligence  \nRenmin University of China Beijing, China [zhewei@ruc.edu.cn](zhewei@ruc.edu.cn)  \narXiv :2607 .03007v 1 [ cs .LG] 3 Jul 2026  \nAbstract  \nRecent advances in molecular large language models have led to strong performance on molecular understanding and generation tasks, yet these gains often come without reliable structural grounding. In particular, existing approaches conflict with the chemistry principle that structure determines function: despite their downstream success, current molecular LLMs perform poorly on basic structure recognition, suggesting that they fail to capture molecular graphs from canonical SMILES. To remedy this, we propose MolBasic, a structure-first framework that strengthens structural comprehension via SMILES–Graph translation. MolBasic is built around a multi-level structure perception benchmark, where bidirectional SMILES–Graph conversion serves as the core task to align sequential and topological representations. On top of this foundation, we employ a progressive learning scheme with a standardized Chain-of-Thought (CoT) to steer models from structure acquisition toward higherlevel molecular reasoning. Experiments show that MolBasic substantially improves structural understanding and yields robust gains on downstream tasks, including property prediction and objective optimization, supporting our structure-first paradigm.  \n1 Introduction  \nUnderstanding molecular characteristics and properties through structural analysis, and designing molecules for specific objectives, has long been a central focus of research in biochemistry. This effort is of fundamental importance for advancing drug mechanism studies and the design of novel drugs. With the continuous improvement of Large Language Models (LLMs) in learning and reasoning, more studies are exploring how to leverage the domain knowledge embedded in these models for molecular understanding tasks. Compared to manual analysis, LLMs offer clear advantages in  \nFigure 1: Preliminary evaluation of generalist and molecular specialist LLMs on basic structure comprehension tasks (atom counting and bond counting) using a pilot dataset sampled from PubChem (Kim et al., 2023) . Results reveal that current LLMs fail to capture fundamental graph structure information from SMILES.  \nterms of cost and efficiency, making them an ideal tool for this purpose. Therefore, developing an “AI chemist” capable of structural understanding and reasoning of molecular compounds is crucial.  \nGeneralist LLMs, such as GPT (Floridi and Chiriatti, 2020 ; OpenAI, 2023), Qwen (Bai et al., 2023), T5 (Raffel et al., 2020), InternLM (Team, 2023), Vicuna (Zheng et al., 2023), and ChatGLM (GLM et al., 2024), acquire knowledge across diverse domains during pre-training and thus possess certain molecular understanding capabilities. However, their knowledge is primarily derived from medical or biological texts related to molecules, which grants them basic knowledge retrieval abilities, rather than genuine structural comprehension. Of course, models with strong reasoning and mathematical capabilities, such as GPT-5 (Singh et al., 2025), can achieve molecular understanding through tool invocation and mathematical computation. Molecular specialist LLMs, on the other hand, are the mainstream approach for LLM-based molecular understanding. Existing research predominantly focuses on two directions: (i) designing molecular representations that facilitate model comprehension—for instance, HIGHT (Chen et al., 2024a) employs multi-level molecular representation","cbCaiatM4vXeDfKF","https://ap.wps.com/l/cbCaiatM4vXeDfKF","pdf",3500134,22,"English","# Introduction\n## Motivation: structure determines function\n## Limitations of existing molecular LLM paradigms\n## Proposed framework: MolBasic\n# Preliminary evaluation and comparison\n## Basic structural perception results","[{\"question\":\"How does MolBasic help models move from structure acquisition to higher-level reasoning?\",\"answer\":\"It adds a progressive learning scheme with a standardized Chain-of-Thought (CoT) to guide learning from structural acquisition toward higher-level molecular reasoning.\"}]","Back to Basics - Improving Molecular Understanding in LLMs via SMILES - Graph Translation | PDF",1789977702,55]