{"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/pulsar-at-mediqa-sum-2023-large-language","title":"PULSAR at MEDIQA-Sum 2023: Large Language Models Augmented by Synthetic Dialogue Convert Patient Dialogues to Medical Records","arxiv_id":"2307.02006","date":"2023-07-05","proceeding":null,"authors":["Viktor Schlegel","Hao Li","Yuping Wu","Anand Subramanian","Thanh-Tung Nguyen","Abhinav Ramesh Kashyap","Daniel Beck","Xiaojun Zeng","Riza Theresa Batista-Navarro","Stefan Winkler","Goran Nenadic"],"abstract":"This paper describes PULSAR, our system submission at the ImageClef 2023 MediQA-Sum task on summarising patient-doctor dialogues into clinical records. The proposed framework relies on domain-specific pre-training, to produce a specialised language model which is trained on task-specific natural data augmented by synthetic data generated by a black-box LLM. We find limited evidence towards the efficacy of domain-specific pre-training and data augmentation, while scaling up the language model yields the best performance gains. Our approach was ranked second and third among 13 submissions on task B of the challenge. Our code is available at https://github.com/yuping-wu/PULSAR.","url_abs":"https://arxiv.org/abs/2307.02006v1","url_pdf":"https://arxiv.org/pdf/2307.02006v1.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":"pulsar-at-mediqa-sum-2023-large-language","repo_url":"https://github.com/yuping-wu/pulsar","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2307.02006","atlas_url":"https://app.syntology.ai/?focus=2307.02006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.02006"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/yuping-wu/pulsar","reach":{"status":"ok"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"ran":0,"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":7,"samples":[{"code_sha256_prefix":"74b86dabed4a8faf","entry":"compute_metrics","repo":"yuping-wu/pulsar","repo_kind":"official","path":"fine-tune/bionlp2023_finetune.py","file_url":"https://github.com/yuping-wu/pulsar/blob/HEAD/fine-tune/bionlp2023_finetune.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"74b86dabed4a8faf"}},{"code_sha256_prefix":"ba062792c531bce5","entry":"load_dataset","repo":"yuping-wu/pulsar","repo_kind":"official","path":"fine-tune/clef_finetune_accelerate.py","file_url":"https://github.com/yuping-wu/pulsar/blob/HEAD/fine-tune/clef_finetune_accelerate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ba062792c531bce5"}},{"code_sha256_prefix":"1bbc6b60760b9778","entry":"load_dataset","repo":"yuping-wu/pulsar","repo_kind":"official","path":"fine-tune/clef_finetune_accelerate_taskc.py","file_url":"https://github.com/yuping-wu/pulsar/blob/HEAD/fine-tune/clef_finetune_accelerate_taskc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1bbc6b60760b9778"}},{"code_sha256_prefix":"ad5a1fa906311d2d","entry":"preprocess_function","repo":"yuping-wu/pulsar","repo_kind":"official","path":"fine-tune/bionlp2023_finetune.py","file_url":"https://github.com/yuping-wu/pulsar/blob/HEAD/fine-tune/bionlp2023_finetune.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ad5a1fa906311d2d"}},{"code_sha256_prefix":"c211c320be482d4d","entry":"preprocess_function","repo":"yuping-wu/pulsar","repo_kind":"official","path":"fine-tune/bionlp2023_finetune_predict_only_v1.py","file_url":"https://github.com/yuping-wu/pulsar/blob/HEAD/fine-tune/bionlp2023_finetune_predict_only_v1.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c211c320be482d4d"}},{"code_sha256_prefix":"7e5ba5df5548eb15","entry":"preprocess_function","repo":"yuping-wu/pulsar","repo_kind":"official","path":"fine-tune/clef_finetune.py","file_url":"https://github.com/yuping-wu/pulsar/blob/HEAD/fine-tune/clef_finetune.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7e5ba5df5548eb15"}},{"code_sha256_prefix":"068495d715fb4c08","entry":"process_data","repo":"yuping-wu/pulsar","repo_kind":"official","path":"fine-tune/bionlp2023_finetune_predict_only_v1.py","file_url":"https://github.com/yuping-wu/pulsar/blob/HEAD/fine-tune/bionlp2023_finetune_predict_only_v1.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"068495d715fb4c08"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}