{"id":"https://openalex.org/W7104368912","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1305","title":"AutoMIR: Effective Zero-Shot Medical Information Retrieval without Relevance Labels","display_name":"AutoMIR: Effective Zero-Shot Medical Information Retrieval without Relevance Labels","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7104368912","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1305"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1305","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1305","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1305.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1305.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Lei Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xiangxu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangxu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xiao Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Zheng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng Liu","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.5483046,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24028","last_page":"24047"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.4796000123023987,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.4796000123023987,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.05770000070333481,"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":0.0568000003695488,"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/relevance","display_name":"Relevance (law)","score":0.6794999837875366},{"id":"https://openalex.org/keywords/medical-information","display_name":"Medical information","score":0.4221999943256378},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.396699994802475},{"id":"https://openalex.org/keywords/information-system","display_name":"Information system","score":0.31929999589920044},{"id":"https://openalex.org/keywords/human\u2013computer-information-retrieval","display_name":"Human\u2013computer information retrieval","score":0.257099986076355}],"concepts":[{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6794999837875366},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6087999939918518},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5060999989509583},{"id":"https://openalex.org/C3019150057","wikidata":"https://www.wikidata.org/wiki/Q92779279","display_name":"Medical information","level":2,"score":0.4221999943256378},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3871999979019165},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2863999903202057},{"id":"https://openalex.org/C90288658","wikidata":"https://www.wikidata.org/wiki/Q3318149","display_name":"Human\u2013computer information retrieval","level":3,"score":0.257099986076355},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.24950000643730164}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1305","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1305","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1305.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1305","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1305","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1305.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322499","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7104368912.pdf","grobid_xml":"https://content.openalex.org/works/W7104368912.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Medical":[0,111],"information":[1],"retrieval":[2,32,96,152],"(MIR)":[3],"is":[4],"vital":[5],"for":[6,103,140],"accessing":[7],"knowledge":[8],"from":[9],"electronic":[10],"health":[11],"records,":[12],"scientific":[13],"literature,":[14],"and":[15,26,95,127,158,163],"medical":[16,22,35,75,122],"databases,":[17],"supporting":[18],"applications":[19],"such":[20],"as":[21],"education,":[23],"patient":[24],"queries,":[25],"clinical":[27],"diagnosis.However,":[28],"effective":[29],"zero-shot":[30],"dense":[31,78],"in":[33,151],"the":[34,41,81,101,109],"domain":[36],"remains":[37],"difficult":[38],"due":[39],"to":[40,64],"scarcity":[42],"of":[43],"relevance-labeled":[44],"data.To":[45],"address":[46],"this":[47],"challenge,":[48],"we":[49,107,135],"propose":[50],"Self-Learning":[51],"Hypothetical":[52],"Document":[53],"Embeddings":[54],"(SL-HyDE),":[55],"a":[56,70,87,116,137],"framework":[57],"that":[58,90,146],"leverages":[59],"large":[60],"language":[61],"models":[62,132],"(LLMs)":[63],"generate":[65],"hypothetical":[66],"documents":[67,72],"conditioned":[68],"on":[69,133],"query.These":[71],"encapsulate":[73],"essential":[74],"context,":[76],"guiding":[77],"retrievers":[79],"toward":[80],"most":[82],"relevant":[83],"results.SL-HyDE":[84],"further":[85],"employs":[86],"self-learning":[88],"mechanism":[89],"iteratively":[91],"improves":[92],"pseudo-document":[93],"generation":[94],"using":[97],"unlabeled":[98],"corpora,":[99],"eliminating":[100],"need":[102],"labeled":[104],"data.In":[105],"addition,":[106],"introduce":[108],"Chinese":[110],"Information":[112],"Retrieval":[113],"Benchmark":[114],"(CMIRB),":[115],"comprehensive":[117],"evaluation":[118],"suite":[119],"reflecting":[120],"real-world":[121],"scenarios,":[123],"comprising":[124],"five":[125],"tasks":[126],"ten":[128,131],"datasets.By":[129],"benchmarking":[130],"CMIRB,":[134],"provide":[136],"rigorous":[138],"standard":[139],"evaluating":[141],"MIR":[142],"systems.Experimental":[143],"results":[144],"demonstrate":[145],"SL-HyDE":[147],"significantly":[148],"outperforms":[149],"HyDE":[150],"accuracy,":[153],"while":[154],"exhibiting":[155],"strong":[156],"generalization":[157],"scalability":[159],"across":[160],"diverse":[161],"LLM":[162],"retriever":[164],"configurations.":[165]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}