{"id":"https://openalex.org/W7152587009","doi":"https://doi.org/10.48550/arxiv.2604.06684","title":"GraphWalker: Patient Analogy Meets Information Gain for Clinical Reasoning with Large Language Models","display_name":"GraphWalker: Patient Analogy Meets Information Gain for Clinical Reasoning with Large Language Models","publication_year":2026,"publication_date":"2026-04-08","ids":{"openalex":"https://openalex.org/W7152587009","doi":"https://doi.org/10.48550/arxiv.2604.06684"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.06684","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06684","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.06684","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133270392","display_name":"Yue Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Yue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133243096","display_name":"Weibin Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liao, Weibin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133246272","display_name":"Yuxin Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yuxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129669965","display_name":"Jiaran Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Jiaran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133248851","display_name":"Hongxin Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Hongxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100648800","display_name":"Jinyang Zhang","orcid":"https://orcid.org/0000-0003-0984-3218"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jinyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011124718","display_name":"Xinke Jiang","orcid":"https://orcid.org/0000-0003-4539-4157"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Xinke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133238291","display_name":"Zhibang Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Zhibang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133279287","display_name":"Junfeng Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Junfeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133249672","display_name":"Yasha Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yasha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133247706","display_name":"Liantao Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Liantao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9661999940872192,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9661999940872192,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.020600000396370888,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.006599999964237213,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5546000003814697},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.46939998865127563},{"id":"https://openalex.org/keywords/health-records","display_name":"Health records","score":0.45260000228881836},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4471000134944916},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3840999901294708},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.35839998722076416},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.35670000314712524},{"id":"https://openalex.org/keywords/cohort","display_name":"Cohort","score":0.35499998927116394},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.34610000252723694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6782000064849854},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5546000003814697},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5465999841690063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.525600016117096},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.46939998865127563},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.45260000228881836},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4471000134944916},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3840999901294708},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C72563966","wikidata":"https://www.wikidata.org/wiki/Q1303415","display_name":"Cohort","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.34610000252723694},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.33809998631477356},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33399999141693115},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.33239999413490295},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3237000107765198},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31040000915527344},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C45827449","wikidata":"https://www.wikidata.org/wiki/Q5270338","display_name":"Diagnosis code","level":3,"score":0.2842999994754791},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.06684","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06684","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.06684","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06684","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7196301817893982}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Clinical":[0],"reasoning":[1,37,58,187],"over":[2,107],"electronic":[3],"health":[4],"records":[5],"(EHRs)":[6],"is":[7,202],"a":[8,22,97,132,192],"fundamental":[9],"yet":[10],"challenging":[11],"task":[12],"in":[13,41,126,196],"modern":[14],"healthcare.":[15],"While":[16],"large":[17],"language":[18],"models":[19],"(LLMs)":[20],"offer":[21],"promising":[23],"paradigm":[24],"via":[25],"in-context":[26],"demonstrations":[27,73,91,141],"that":[28,100,155],"requires":[29],"no":[30],"task-specific":[31,173],"parameter":[32,174],"updates,":[33],"existing":[34],"methods":[35],"for":[36],"by":[38,65,105],"patient":[39,109,121],"analogy":[40,106],"EHR":[42,152],"settings":[43],"suffer":[44],"from":[45],"three":[46],"core":[47],"limitations:":[48],"(1)":[49],"Perspective":[50],"Limitation,":[51],"where":[52,85],"data-driven":[53,115],"similarity":[54],"misaligns":[55],"with":[56,136,142,185],"LLM":[57],"needs":[59],"while":[60],"model-driven":[61,117],"signals":[62],"are":[63,74,92],"constrained":[64],"limited":[66],"clinical":[67,198],"competence;":[68],"(2)":[69],"Cohort":[70],"Awareness,":[71],"as":[72,191],"selected":[75],"independently":[76],"without":[77,172],"modeling":[78],"population-level":[79,127],"structure;":[80],"and":[81,87,116,129,163,182],"(3)":[82],"Information":[83],"Aggregation,":[84],"redundancy":[86],"interaction":[88],"effects":[89],"among":[90],"ignored.":[93],"We":[94],"propose":[95],"GraphWalker,":[96],"training-free":[98],"framework":[99],"lets":[101],"frozen":[102],"LLMs":[103,181],"reason":[104],"retrieved":[108],"cases.":[110],"GraphWalker":[111,156,176],"(i)":[112],"jointly":[113],"leverages":[114],"perspectives,":[118],"(ii)":[119],"discovers":[120],"cohorts":[122],"to":[123,139,179],"ground":[124],"retrieval":[125],"structure,":[128],"(iii)":[130],"employs":[131],"lazy":[133],"greedy":[134],"search":[135],"frontier":[137],"expansion":[138],"compose":[140],"high":[143],"marginal":[144],"information":[145],"gain.":[146],"Extensive":[147],"experiments":[148],"on":[149],"multiple":[150],"real-world":[151],"benchmarks":[153],"show":[154],"consistently":[157],"outperforms":[158],"state-of-the-art":[159],"demonstration":[160],"selection":[161],"baselines,":[162],"remains":[164],"substantially":[165],"more":[166],"robust":[167],"under":[168],"cross-dataset":[169],"distribution":[170],"shift,":[171],"updates.":[175],"further":[177],"generalizes":[178],"black-box":[180],"composes":[183],"naturally":[184],"agentic":[186],"frameworks,":[188],"positioning":[189],"it":[190],"pluggable":[193],"patient-analogy":[194],"skill":[195],"LLM-based":[197],"workflows.":[199],"Our":[200],"code":[201],"available":[203],"at":[204],"https://github.com/PuppyKnightUniversity/GraphWalker.":[205]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-10T00:00:00"}