{"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/a-data-centric-approach-to-generate-faithful","title":"A Data-Centric Approach To Generate Faithful and High Quality Patient Summaries with Large Language Models","arxiv_id":"2402.15422","date":"2024-02-23","proceeding":null,"authors":["Stefan Hegselmann","Shannon Zejiang Shen","Florian Gierse","Monica Agrawal","David Sontag","Xiaoyi Jiang"],"abstract":"Patients often face difficulties in understanding their hospitalizations, while healthcare workers have limited resources to provide explanations. In this work, we investigate the potential of large language models to generate patient summaries based on doctors' notes and study the effect of training data on the faithfulness and quality of the generated summaries. To this end, we release (i) a rigorous labeling protocol for errors in medical texts and (ii) a publicly available dataset of annotated hallucinations in 100 doctor-written and 100 generated summaries. We show that fine-tuning on hallucination-free data effectively reduces hallucinations from 2.60 to 1.55 per summary for Llama 2, while preserving relevant information. We observe a similar effect on GPT-4 (0.70 to 0.40), when the few-shot examples are hallucination-free. We also conduct a qualitative evaluation using hallucination-free and improved training data. We find that common quantitative metrics do not correlate well with faithfulness and quality. Finally, we test GPT-4 for automatic hallucination detection, which clearly outperforms common baselines.","url_abs":"https://arxiv.org/abs/2402.15422v2","url_pdf":"https://arxiv.org/pdf/2402.15422v2.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":"a-data-centric-approach-to-generate-faithful","repo_url":"https://github.com/stefanhgm/patient_summaries_with_llms","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"}],"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":"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":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.15422","atlas_url":"https://app.syntology.ai/?focus=2402.15422","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15422"}},"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/stefanhgm/patient_summaries_with_llms","reach":null}],"summary":{"ran_draft_wrong":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":"1dfa22c583d35631","entry":"create_icl_example_v1","repo":"stefanhgm/patient_summaries_with_llms","repo_kind":"official","path":"gpt-4/run_hallucination_detection.py","file_url":"https://github.com/stefanhgm/patient_summaries_with_llms/blob/HEAD/gpt-4/run_hallucination_detection.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":"1dfa22c583d35631"}},{"code_sha256_prefix":"34f40108fd90e5f1","entry":"extract_di","repo":"stefanhgm/patient_summaries_with_llms","repo_kind":"official","path":"preprocess/process_mimic_summaries.py","file_url":"https://github.com/stefanhgm/patient_summaries_with_llms/blob/HEAD/preprocess/process_mimic_summaries.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"34f40108fd90e5f1"}},{"code_sha256_prefix":"d6b6f331b351e1a3","entry":"extract_hc","repo":"stefanhgm/patient_summaries_with_llms","repo_kind":"official","path":"preprocess/process_mimic_summaries.py","file_url":"https://github.com/stefanhgm/patient_summaries_with_llms/blob/HEAD/preprocess/process_mimic_summaries.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d6b6f331b351e1a3"}},{"code_sha256_prefix":"c40d85bacef9a266","entry":"parse_hallucination_detection_results","repo":"stefanhgm/patient_summaries_with_llms","repo_kind":"official","path":"gpt-4/run_hallucination_detection.py","file_url":"https://github.com/stefanhgm/patient_summaries_with_llms/blob/HEAD/gpt-4/run_hallucination_detection.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":"c40d85bacef9a266"}},{"code_sha256_prefix":"115edd746212499f","entry":"remove_empty_and_short_summaries","repo":"stefanhgm/patient_summaries_with_llms","repo_kind":"official","path":"preprocess/process_mimic_summaries.py","file_url":"https://github.com/stefanhgm/patient_summaries_with_llms/blob/HEAD/preprocess/process_mimic_summaries.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":"115edd746212499f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}