{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/llasmol-advancing-large-language-models-for","title":"LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset","arxiv_id":"2402.09391","date":"2024-02-14","proceeding":null,"authors":["Botao Yu","Frazier N. Baker","Ziqi Chen","Xia Ning","Huan Sun"],"abstract":"Chemistry plays a crucial role in many domains, such as drug discovery and material science. While large language models (LLMs) such as GPT-4 exhibit remarkable capabilities on natural language processing tasks, existing research indicates that their performance on chemistry tasks is discouragingly low. In this paper, however, we demonstrate that our developed LLMs can achieve very strong results on a comprehensive set of chemistry tasks, outperforming the most advanced GPT-4 and Claude 3 Opus by a substantial margin. To accomplish this, we propose SMolInstruct, a large-scale, comprehensive, and high-quality dataset for instruction tuning. It contains 14 selected chemistry tasks and over three million samples, laying a solid foundation for training and evaluating LLMs for chemistry. Using SMolInstruct, we fine-tune a set of open-source LLMs, among which, we find that Mistral serves as the best base model for chemistry tasks. Our analysis further demonstrates the critical role of the proposed dataset in driving the performance improvements.","url_abs":"https://arxiv.org/abs/2402.09391v4","url_pdf":"https://arxiv.org/pdf/2402.09391v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"llasmol-advancing-large-language-models-for","repo_url":"https://github.com/osu-nlp-group/llm4chem","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"drug-discovery","task_name":"Drug Discovery"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"base","method_name":"BASE"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"set","method_name":"SET"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.09391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09391"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/osu-nlp-group/llm4chem","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":8,"unverified":1},"by_repo_kind":{"official":{"samples":9,"ran":8,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2e77e03994ffa26f","entry":"extract_answer_part","repo":"osu-nlp-group/llm4chem","repo_kind":"official","path":"extract_prediction.py","file_url":"https://github.com/osu-nlp-group/llm4chem/blob/HEAD/extract_prediction.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2e77e03994ffa26f"}},{"code_sha256_prefix":"567166dd32d98725","entry":"find_sub_sequence","repo":"osu-nlp-group/llm4chem","repo_kind":"official","path":"utils/core_tagger.py","file_url":"https://github.com/osu-nlp-group/llm4chem/blob/HEAD/utils/core_tagger.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"567166dd32d98725"}},{"code_sha256_prefix":"48d115e8555fdcc7","entry":"generate_chat","repo":"osu-nlp-group/llm4chem","repo_kind":"official","path":"utils/chat_generation.py","file_url":"https://github.com/osu-nlp-group/llm4chem/blob/HEAD/utils/chat_generation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"48d115e8555fdcc7"}},{"code_sha256_prefix":"78558afc3dc5a615","entry":"get_chat_content","repo":"osu-nlp-group/llm4chem","repo_kind":"official","path":"utils/general_prompter.py","file_url":"https://github.com/osu-nlp-group/llm4chem/blob/HEAD/utils/general_prompter.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"78558afc3dc5a615"}},{"code_sha256_prefix":"6bb075d04572d7e3","entry":"llama_forward_synthesis","repo":"osu-nlp-group/llm4chem","repo_kind":"official","path":"prediction_extraction.py","file_url":"https://github.com/osu-nlp-group/llm4chem/blob/HEAD/prediction_extraction.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6bb075d04572d7e3"}},{"code_sha256_prefix":"52df787328283db4","entry":"llama_molecule_generation","repo":"osu-nlp-group/llm4chem","repo_kind":"official","path":"prediction_extraction.py","file_url":"https://github.com/osu-nlp-group/llm4chem/blob/HEAD/prediction_extraction.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"52df787328283db4"}},{"code_sha256_prefix":"08641ffa37ef2d2f","entry":"llama_retrosynthesis","repo":"osu-nlp-group/llm4chem","repo_kind":"official","path":"prediction_extraction.py","file_url":"https://github.com/osu-nlp-group/llm4chem/blob/HEAD/prediction_extraction.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"08641ffa37ef2d2f"}},{"code_sha256_prefix":"b8dc6f087d9f1731","entry":"read_result","repo":"osu-nlp-group/llm4chem","repo_kind":"official","path":"compute_metrics.py","file_url":"https://github.com/osu-nlp-group/llm4chem/blob/HEAD/compute_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b8dc6f087d9f1731"}},{"code_sha256_prefix":"adcef27608cdbd15","entry":"tokenize","repo":"osu-nlp-group/llm4chem","repo_kind":"official","path":"generation.py","file_url":"https://github.com/osu-nlp-group/llm4chem/blob/HEAD/generation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"adcef27608cdbd15"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}