{"id":"https://openalex.org/W7135054945","doi":"https://doi.org/10.48550/arxiv.2603.10560","title":"PET-F2I: A Comprehensive Benchmark and Parameter-Efficient Fine-Tuning of LLMs for PET/CT Report Impression Generation","display_name":"PET-F2I: A Comprehensive Benchmark and Parameter-Efficient Fine-Tuning of LLMs for PET/CT Report Impression Generation","publication_year":2026,"publication_date":"2026-03-11","ids":{"openalex":"https://openalex.org/W7135054945","doi":"https://doi.org/10.48550/arxiv.2603.10560"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.10560","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10560","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.2603.10560","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128875779","display_name":"Yuchen Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yuchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128866451","display_name":"Wenbo Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wenbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005054660","display_name":"Liling Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Liling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128895616","display_name":"Yichi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yichi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128829735","display_name":"Yu V. Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128828566","display_name":"Xin Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128814448","display_name":"Chao Qu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qu, Chao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128881505","display_name":"Yuan Qi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi, Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128913029","display_name":"Le Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Le","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/T10028","display_name":"Topic Modeling","score":0.3880999982357025,"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/T10028","display_name":"Topic Modeling","score":0.3880999982357025,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1460999995470047,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.1354999989271164,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8080000281333923},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6696000099182129},{"id":"https://openalex.org/keywords/frontier","display_name":"Frontier","score":0.45590001344680786},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45100000500679016},{"id":"https://openalex.org/keywords/completeness","display_name":"Completeness (order theory)","score":0.373199999332428},{"id":"https://openalex.org/keywords/impression","display_name":"Impression","score":0.3474000096321106}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8080000281333923},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6696000099182129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5479000210762024},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.45590001344680786},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45100000500679016},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.4343000054359436},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40869998931884766},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C2776684213","wikidata":"https://www.wikidata.org/wiki/Q6007582","display_name":"Impression","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C4994750","wikidata":"https://www.wikidata.org/wiki/Q1210504","display_name":"Impression management","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.320499986410141},{"id":"https://openalex.org/C41458344","wikidata":"https://www.wikidata.org/wiki/Q732577","display_name":"Publication","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C512654426","wikidata":"https://www.wikidata.org/wiki/Q19652","display_name":"Public domain","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2985999882221222},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.2678000032901764},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25220000743865967},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.25189998745918274},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.10560","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10560","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.2603.10560","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10560","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":[{"id":"https://metadata.un.org/sdg/8","score":0.4457937479019165,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"PET/CT":[0,36,49],"imaging":[1],"is":[2,17],"pivotal":[3],"in":[4,24,30,139,155,165],"oncology":[5],"and":[6,77,80,116,126,151,168,186],"nuclear":[7],"medicine,":[8],"yet":[9],"summarizing":[10],"complex":[11],"findings":[12],"into":[13],"precise":[14],"diagnostic":[15,124],"impressions":[16],"labor-intensive.":[18],"While":[19],"LLMs":[20,136],"have":[21],"shown":[22],"promise":[23],"medical":[25],"text":[26],"generation,":[27],"their":[28],"capability":[29],"the":[31,159,182],"highly":[32],"specialized":[33],"domain":[34],"of":[35,67,184],"remains":[37],"underexplored.":[38],"We":[39],"introduce":[40],"PET-F2I-41K":[41,174],"(PET":[42],"Findings-to-Impression":[43],"Benchmark),":[44],"a":[45,64,83,152,176],"large-scale":[46],"benchmark":[47],"for":[48,191],"impression":[50],"generation":[51],"using":[52],"LLMs,":[53,73,79],"constructed":[54],"from":[55,89],"over":[56,158],"41k":[57],"real-world":[58],"reports.":[59],"Using":[60],"PET-F2I-41K,":[61],"we":[62,81,101],"conduct":[63],"comprehensive":[65],"evaluation":[66,178],"27":[68],"models":[69],"across":[70],"proprietary":[71],"frontier":[72,133],"open-source":[74],"generalist":[75],"models,":[76],"medical-domain":[78,135],"develop":[82],"domain-adapted":[84],"7B":[85],"model":[86],"(PET-F2I-7B)":[87],"fine-tuned":[88],"Qwen2.5-7B-Instruct":[90],"via":[91],"LoRA.":[92],"Beyond":[93,170],"standard":[94],"NLG":[95],"metrics":[96,106],"(e.g.,":[97,148],"BLEU-4,":[98],"ROUGE-L,":[99],"BERTScore),":[100],"propose":[102],"three":[103],"clinically":[104,187],"grounded":[105],"-":[107,121],"Entity":[108,113],"Coverage":[109],"Rate":[110,114,119],"(ECR),":[111],"Uncovered":[112],"(UER),":[115],"Factual":[117],"Consistency":[118],"(FCR)":[120],"to":[122,180],"assess":[123],"completeness":[125],"factual":[127],"reliability.":[128],"Experiments":[129],"reveal":[130],"that":[131],"neither":[132],"nor":[134],"perform":[137],"adequately":[138],"zero-shot":[140],"settings.":[141],"In":[142],"contrast,":[143],"PET-F2I-7B":[144],"achieves":[145],"substantial":[146],"gains":[147],"0.708":[149],"BLEU-4)":[150],"3.0x":[153],"improvement":[154],"entity":[156],"coverage":[157],"strongest":[160],"baseline,":[161],"while":[162],"offering":[163],"advantages":[164],"cost,":[166],"latency,":[167],"privacy.":[169],"this":[171],"modeling":[172],"contribution,":[173],"establishes":[175],"standardized":[177],"framework":[179],"accelerate":[181],"development":[183],"reliable":[185],"deployable":[188],"reporting":[189],"systems":[190],"PET/CT.":[192]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-13T00:00:00"}