{"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/knowledge-infused-prompting-assessing-and","title":"Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language Models","arxiv_id":"2311.00287","date":"2023-11-01","proceeding":null,"authors":["ran Xu","Hejie Cui","Yue Yu","Xuan Kan","Wenqi Shi","Yuchen Zhuang","Wei Jin","Joyce Ho","Carl Yang"],"abstract":"Clinical natural language processing requires methods that can address domain-specific challenges, such as complex medical terminology and clinical contexts. Recently, large language models (LLMs) have shown promise in this domain. Yet, their direct deployment can lead to privacy issues and are constrained by resources. To address this challenge, we delve into synthetic clinical text generation using LLMs for clinical NLP tasks. We propose an innovative, resource-efficient approach, ClinGen, which infuses knowledge into the process. Our model involves clinical knowledge extraction and context-informed LLM prompting. Both clinical topics and writing styles are drawn from external domain-specific knowledge graphs and LLMs to guide data generation. Our extensive empirical study across 7 clinical NLP tasks and 16 datasets reveals that ClinGen consistently enhances performance across various tasks, effectively aligning the distribution of real datasets and significantly enriching the diversity of generated training instances. Our code is available at \\url{https://github.com/ritaranx/ClinGen}.","url_abs":"https://arxiv.org/abs/2311.00287v2","url_pdf":"https://arxiv.org/pdf/2311.00287v2.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":"knowledge-infused-prompting-assessing-and","repo_url":"https://github.com/ritaranx/clingen","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"clinical-knowledge","task_name":"Clinical Knowledge"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2311.00287","atlas_url":"https://app.syntology.ai/?focus=2311.00287","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.00287"}},"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/ritaranx/clingen","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":1,"samples":[{"code_sha256_prefix":"2fd46a9fc43fa059","entry":"clean_str","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"2fd46a9fc43fa059"}},{"code_sha256_prefix":"a7029bb10835862d","entry":"load_demo","repo":"ritaranx/clingen","repo_kind":"official","path":"src/medication_attr/clingen.py","file_url":"https://github.com/ritaranx/clingen/blob/HEAD/src/medication_attr/clingen.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a7029bb10835862d"}},{"code_sha256_prefix":"bcbcbcb872ce2071","entry":"load_demo","repo":"ritaranx/clingen","repo_kind":"official","path":"src/nli/clingen_step1.py","file_url":"https://github.com/ritaranx/clingen/blob/HEAD/src/nli/clingen_step1.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bcbcbcb872ce2071"}},{"code_sha256_prefix":"3b72e169f6be0118","entry":"load_demo","repo":"ritaranx/clingen","repo_kind":"official","path":"src/ner/clingen.py","file_url":"https://github.com/ritaranx/clingen/blob/HEAD/src/ner/clingen.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":"3b72e169f6be0118"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}