{"url":"/dataset/pubchemqa","name":"PubChemQA","full_name":null,"description_markdown":"PubChemQA consists of molecules and their corresponding textual descriptions from PubChem. It contains a single type of question, i.e., please describe the molecule. We remove molecules that cannot be processed by RDKit [Landrum et al., 2021] to generate 2D molecular graphs. We also remove texts with less than 4 words, and crops descriptions with more than 256 words. Finally, we obtain 325, 754 unique molecules and 365, 129 molecule-text pairs. On average, each text description contains 17 words.","description_withheld":null,"homepage":"https://github.com/PharMolix/OpenBioMed","introduced_date":"2023-08-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/biomedgpt-open-multimodal-generative-pre","title":"BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine","first_author":null,"url":null},"license":{"name":"MIT","url":null},"modalities":[],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["PubChemQA"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-pubchemqa","task":"Question Answering","dataset_variant":"PubChemQA","rows":2,"metrics":["BLEU-2","BLEU-4","ROUGE-1","ROUGE-2","ROUGE-L","MEATOR"],"first_row_in_archive_order":{"model":"BioMedGPT-10B","paper":"/paper/biomedgpt-open-multimodal-generative-pre","metrics":{"BLEU-2":"0.234","BLEU-4":"0.141","MEATOR":"0.308","ROUGE-1":"0.386","ROUGE-2":"0.206","ROUGE-L":"0.332"},"code_links":[{"title":"pharmolix/openbiomed","url":"https://github.com/pharmolix/openbiomed"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/biomedgpt-open-multimodal-generative-pre","title":"BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine","date":"2023-08-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/llama-2-open-foundation-and-fine-tuned-chat","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","date":"2023-07-18","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":52,"samples_ran":31,"samples_unverified":21,"pointer_only_for_licence":16,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":52,"samples_ran":31,"samples_unverified":21,"pointer_only_for_licence":16,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}