{"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/famesumm-investigating-and-improving","title":"FaMeSumm: Investigating and Improving Faithfulness of Medical Summarization","arxiv_id":"2311.02271","date":"2023-11-03","proceeding":null,"authors":["Nan Zhang","Yusen Zhang","Wu Guo","Prasenjit Mitra","Rui Zhang"],"abstract":"Summaries of medical text shall be faithful by being consistent and factual with source inputs, which is an important but understudied topic for safety and efficiency in healthcare. In this paper, we investigate and improve faithfulness in summarization on a broad range of medical summarization tasks. Our investigation reveals that current summarization models often produce unfaithful outputs for medical input text. We then introduce FaMeSumm, a framework to improve faithfulness by fine-tuning pre-trained language models based on medical knowledge. FaMeSumm performs contrastive learning on designed sets of faithful and unfaithful summaries, and it incorporates medical terms and their contexts to encourage faithful generation of medical terms. We conduct comprehensive experiments on three datasets in two languages: health question and radiology report summarization datasets in English, and a patient-doctor dialogue dataset in Chinese. Results demonstrate that FaMeSumm is flexible and effective by delivering consistent improvements over mainstream language models such as BART, T5, mT5, and PEGASUS, yielding state-of-the-art performances on metrics for faithfulness and general quality. Human evaluation by doctors also shows that FaMeSumm generates more faithful outputs. Our code is available at https://github.com/psunlpgroup/FaMeSumm .","url_abs":"https://arxiv.org/abs/2311.02271v2","url_pdf":"https://arxiv.org/pdf/2311.02271v2.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":"famesumm-investigating-and-improving","repo_url":"https://github.com/psunlpgroup/famesumm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"}],"methods":[{"method_slug":"adafactor","method_name":"Adafactor"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bart","method_name":"BART"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"glu","method_name":"Gated Linear Unit"},{"method_slug":"inverse-square-root-schedule","method_name":"Inverse Square Root Schedule"},{"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":"pegasus","method_name":"PEGASUS"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sentencepiece","method_name":"SentencePiece"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"t5","method_name":"T5"},{"method_slug":"mt5","method_name":"mT5"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.02271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.02271"}},"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":"deterministic:regex_extraction","url":"https://github.com/psunlpgroup/FaMeSumm","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"unverified":3},"by_repo_kind":{"official":{"samples":6,"ran":3,"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":"1e2ebb819a8fa6f4","entry":"get_dataset","repo":"psunlpgroup/FaMeSumm","repo_kind":"official","path":"train_BioBART_HQS.py","file_url":"https://github.com/psunlpgroup/FaMeSumm/blob/HEAD/train_BioBART_HQS.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1e2ebb819a8fa6f4"}},{"code_sha256_prefix":"aefc015a9e203048","entry":"get_dataset","repo":"psunlpgroup/FaMeSumm","repo_kind":"official","path":"train_mt5_MDS.py","file_url":"https://github.com/psunlpgroup/FaMeSumm/blob/HEAD/train_mt5_MDS.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aefc015a9e203048"}},{"code_sha256_prefix":"0ba05c51d5e75fa5","entry":"get_dataset","repo":"psunlpgroup/FaMeSumm","repo_kind":"official","path":"train_pega_HQS.py","file_url":"https://github.com/psunlpgroup/FaMeSumm/blob/HEAD/train_pega_HQS.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0ba05c51d5e75fa5"}},{"code_sha256_prefix":"5b2b3cf5fa2ba68e","entry":"get_dataset","repo":"psunlpgroup/FaMeSumm","repo_kind":"official","path":"train_bart_HQS.py","file_url":"https://github.com/psunlpgroup/FaMeSumm/blob/HEAD/train_bart_HQS.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5b2b3cf5fa2ba68e"}},{"code_sha256_prefix":"0720dc4ed40173aa","entry":"get_dataset","repo":"psunlpgroup/FaMeSumm","repo_kind":"official","path":"train_pega_RRS.py","file_url":"https://github.com/psunlpgroup/FaMeSumm/blob/HEAD/train_pega_RRS.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0720dc4ed40173aa"}},{"code_sha256_prefix":"b88daf37a564369f","entry":"get_dataset","repo":"psunlpgroup/FaMeSumm","repo_kind":"official","path":"train_t5_HQS.py","file_url":"https://github.com/psunlpgroup/FaMeSumm/blob/HEAD/train_t5_HQS.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b88daf37a564369f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}