{"id":"https://openalex.org/W7214093351","doi":"https://doi.org/10.64898/2026.09.17.26363288","title":"LitBench: A Benchmark for Retrieval-Grounded Multi-Paper Evidence Synthesis in Epilepsy","display_name":"LitBench: A Benchmark for Retrieval-Grounded Multi-Paper Evidence Synthesis in Epilepsy","publication_year":2026,"publication_date":"2026-09-23","ids":{"openalex":"https://openalex.org/W7214093351","doi":"https://doi.org/10.64898/2026.09.17.26363288","pmid":"https://pubmed.ncbi.nlm.nih.gov/42818145","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13622311"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.17.26363288","doi":"https://doi.org/10.64898/2026.09.17.26363288","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.17.26363288","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/09/23/2026.09.17.26363288.full.pdf","source":{"id":"https://openalex.org/S3005729997","display_name":"medRxiv","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.medrxiv.org/content/medrxiv/early/2026/09/23/2026.09.17.26363288.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5096258884","display_name":"Alon Gorenshtein","orcid":"https://orcid.org/0009-0000-7542-8608","observed_orcids":["https://orcid.org/0009-0000-7542-8608"]},"institutions":[{"id":"https://openalex.org/I1316535847","display_name":"Beth Israel Deaconess Medical Center","ror":"https://ror.org/04drvxt59","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1316535847"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alon Gorenshtein","raw_affiliation_strings":["Department of Neurology, Beth Israel Deaconess Medical Center, Boston, MA, USA","Harvard Medical School, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0009-0000-7542-8608","affiliations":[{"raw_affiliation_string":"Department of Neurology, Beth Israel Deaconess Medical Center, Boston, MA, USA","institution_ids":["https://openalex.org/I1316535847"]},{"raw_affiliation_string":"Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152556643","display_name":"Tianyu Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1316535847","display_name":"Beth Israel Deaconess Medical Center","ror":"https://ror.org/04drvxt59","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1316535847"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyu Zhang","raw_affiliation_strings":["Department of Neurology, Beth Israel Deaconess Medical Center, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Neurology, Beth Israel Deaconess Medical Center, Boston, MA, USA","institution_ids":["https://openalex.org/I1316535847"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023557669","display_name":"Michael Brandon Westover","orcid":"https://orcid.org/0000-0003-4803-312X","observed_orcids":["https://orcid.org/0000-0003-4803-312X"]},"institutions":[{"id":"https://openalex.org/I1316535847","display_name":"Beth Israel Deaconess Medical Center","ror":"https://ror.org/04drvxt59","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1316535847"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Brandon Westover","raw_affiliation_strings":["Department of Neurology, Beth Israel Deaconess Medical Center, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4803-312X","affiliations":[{"raw_affiliation_string":"Department of Neurology, Beth Israel Deaconess Medical Center, Boston, MA, USA","institution_ids":["https://openalex.org/I1316535847"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078502762","display_name":"Daniel M. Goldenholz","orcid":"https://orcid.org/0000-0002-8370-2758","observed_orcids":["https://orcid.org/0000-0002-8370-2758"]},"institutions":[{"id":"https://openalex.org/I1316535847","display_name":"Beth Israel Deaconess Medical Center","ror":"https://ror.org/04drvxt59","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1316535847"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel M. Goldenholz","raw_affiliation_strings":["Department of Neurology, Beth Israel Deaconess Medical Center, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8370-2758","affiliations":[{"raw_affiliation_string":"Department of Neurology, Beth Israel Deaconess Medical Center, Boston, MA, USA","institution_ids":["https://openalex.org/I1316535847"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5096258884"],"corresponding_institution_ids":["https://openalex.org/I1316535847","https://openalex.org/I136199984"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.5073000192642212,"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":0.5073000192642212,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.396699994802475,"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/T10206","display_name":"Meta-analysis and systematic reviews","score":0.01979999989271164,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/evidence-synthesis","display_name":"evidence synthesis","score":0.5740000009536743},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.7940000295639038},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.5799999833106995},{"id":"https://openalex.org/keywords/hallucinations","display_name":"hallucinations","score":0.5040000081062317},{"id":"https://openalex.org/keywords/gemma","display_name":"Gemma","score":0.5529999732971191},{"id":"https://openalex.org/keywords/sonnets","display_name":"sonnets","score":0.8149999976158142},{"id":"https://openalex.org/keywords/deepseek","display_name":"DeepSeek","score":0.8379999995231628}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6622999906539917},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.6097000241279602},{"id":"https://openalex.org/C2778186239","wikidata":"https://www.wikidata.org/wiki/Q41571","display_name":"Epilepsy","level":2,"score":0.5644000172615051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5501000285148621},{"id":"https://openalex.org/C109167261","wikidata":"https://www.wikidata.org/wiki/Q5421955","display_name":"Fell","level":2,"score":0.5396000146865845},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.41130000352859497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39410001039505005},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3465999960899353},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33320000767707825},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C3019144022","wikidata":"https://www.wikidata.org/wiki/Q4124998","display_name":"Questions and answers","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.28200000524520874},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2782000005245209},{"id":"https://openalex.org/C19648533","wikidata":"https://www.wikidata.org/wiki/Q691640","display_name":"Evidence-based medicine","level":3,"score":0.274399995803833},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2689000070095062},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.260699987411499},{"id":"https://openalex.org/C3019480001","wikidata":"https://www.wikidata.org/wiki/Q4896847","display_name":"Best evidence","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.64898/2026.09.17.26363288","doi":"https://doi.org/10.64898/2026.09.17.26363288","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.17.26363288","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/09/23/2026.09.17.26363288.full.pdf","source":{"id":"https://openalex.org/S3005729997","display_name":"medRxiv","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"},{"id":"pmh:oai:pubmedcentral.nih.gov:13622311","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13622311/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13622311/pdf/nihpp-2026.09.17.26363288v1.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"medRxiv","raw_type":"Text"},{"id":"pmid:42818145","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42818145","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"medRxiv : the preprint server for health sciences","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.64898/2026.09.17.26363288","doi":"https://doi.org/10.64898/2026.09.17.26363288","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.17.26363288","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/09/23/2026.09.17.26363288.full.pdf","source":{"id":"https://openalex.org/S3005729997","display_name":"medRxiv","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3431488302","display_name":"Comparative effectiveness of EEG-guided anti-seizure treatment in acute brain injury","funder_award_id":"1r01ns131347-01a1","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5578660234","display_name":"Establishing a Brain Health Index","funder_award_id":"RF1NS120947","funder_id":"https://openalex.org/F4320337359","funder_display_name":"National Institute of Neurological Disorders and Stroke"},{"id":"https://openalex.org/G7391076671","display_name":"Late-onset Unexplained Epilepsy as a Risk Factor for Dementia","funder_award_id":"1r01ns130119-01a1","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8176564889","display_name":"Integrative Motor Activity Biomarker for the Risk of Alzheimer's Risk","funder_award_id":"RF1AG064312","funder_id":"https://openalex.org/F4320337337","funder_display_name":"National Institute on Aging"},{"id":"https://openalex.org/G9000869411","display_name":"Non-Invasive Seizure Forecasting System Using E-Diaries, Internal and External Factors","funder_award_id":"K23NS124656","funder_id":"https://openalex.org/F4320337359","funder_display_name":"National Institute of Neurological Disorders and Stroke"},{"id":"https://openalex.org/G9000886227","display_name":"Low Neurophysiologic Resistance to Anesthetics as a Marker of Preclinical/Prodromal Alzheimer's Disease and Neurovascular Pathology, Delirium risk and Inattention","funder_award_id":"R01AG073598","funder_id":"https://openalex.org/F4320337337","funder_display_name":"National Institute on Aging"},{"id":"https://openalex.org/G9000909494","display_name":"Comparative Safety of Seizure Prophylaxis within the Medicare Program","funder_award_id":"R01AG073410","funder_id":"https://openalex.org/F4320337337","funder_display_name":"National Institute on Aging"},{"id":"https://openalex.org/G9000916450","display_name":"Data-Driven Sleep Biomarkers of Brain Health, Heart Health, and Mortality","funder_award_id":"R01HL161253","funder_id":"https://openalex.org/F4320337338","funder_display_name":"National Heart, Lung, and Blood Institute"},{"id":"https://openalex.org/G9000921416","display_name":"Prospective Validation of Neurophysiologic Outcome Prediction in Acute Brain Injury","funder_award_id":"R01NS126282","funder_id":"https://openalex.org/F4320337359","funder_display_name":"National Institute of Neurological Disorders and Stroke"}],"funders":[{"id":"https://openalex.org/F4320315054","display_name":"American Board of Psychiatry and Neurology","ror":"https://ror.org/00rq2r705"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337337","display_name":"National Institute on Aging","ror":"https://ror.org/049v75w11"},{"id":"https://openalex.org/F4320337338","display_name":"National Heart, Lung, and Blood Institute","ror":"https://ror.org/012pb6c26"},{"id":"https://openalex.org/F4320337359","display_name":"National Institute of Neurological Disorders and Stroke","ror":"https://ror.org/01s5ya894"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214093351.pdf","grobid_xml":"https://content.openalex.org/works/W7214093351.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1981208470","https://openalex.org/W2023155726","https://openalex.org/W2963323070","https://openalex.org/W2970482702","https://openalex.org/W3035441651","https://openalex.org/W4384561707","https://openalex.org/W4385571271","https://openalex.org/W4385574202","https://openalex.org/W4389519598","https://openalex.org/W4391221150","https://openalex.org/W4391324456","https://openalex.org/W4393147129","https://openalex.org/W4396570275","https://openalex.org/W4401042562","https://openalex.org/W4402345509","https://openalex.org/W4402670290","https://openalex.org/W4403420208","https://openalex.org/W4403795293","https://openalex.org/W4406152263","https://openalex.org/W4409210035","https://openalex.org/W4412565252","https://openalex.org/W4412888080","https://openalex.org/W4412888154","https://openalex.org/W4412945726","https://openalex.org/W4413051957","https://openalex.org/W7101416451","https://openalex.org/W7124888346","https://openalex.org/W7127589252","https://openalex.org/W7133239970","https://openalex.org/W7160914799","https://openalex.org/W7164566809","https://openalex.org/W7166830541","https://openalex.org/W7168249844"],"related_works":["https://openalex.org/W7152092397","https://openalex.org/W7171651288","https://openalex.org/W4415190644","https://openalex.org/W7213428852","https://openalex.org/W7202129554","https://openalex.org/W7166849214","https://openalex.org/W7167418027","https://openalex.org/W7213523995","https://openalex.org/W7169858658","https://openalex.org/W7162393605"],"abstract_inverted_index":{"Background:":[0],"competing":[1,209],"papers,":[2],"one-versus":[3],"two-paper":[4,102,184,220],"evidence,":[5],"and":[6,29,37,89,129,153,181,225],"refusal":[7,77,160],"when":[8,106],"evidence":[9,157],"is":[10],"absent.":[11],"Methods:":[12],"LitBench":[13,241],"comprises":[14],"1,980":[15],"open-access":[16],"papers":[17,20,137,210],"(1,000":[18],"epilepsy":[19,136],"holding":[21],"the":[22,51,71,79],"answers,":[23],"980":[24],"decoys":[25],"from":[26,42,118,162],"unrelated":[27],"fields)":[28],"9,472":[30],"human-reviewed":[31],"facts,":[32],"giving":[33],"2,188":[34],"single-paper":[35,114,180],"questions":[36,66,103],"170":[38],"requiring":[39],"a":[40],"fact":[41],"each":[43,98],"of":[44,178,193],"two":[45],"papers.":[46],"Difficulty":[47],"rose":[48],"by":[49,100],"burying":[50],"answer":[52,99],"among":[53],"up":[54],"to":[55,120,125,131,164],"2,000":[56],"distractors,":[57],"then":[58,68],"again":[59],"over":[60],"live":[61],"PubMed":[62],"Central.":[63],"The":[64],"same":[65],"were":[67,84,109,138,211,215],"asked":[69],"with":[70],"answering":[72],"paper":[73],"removed,":[74],"so":[75],"that":[76],"was":[78,150,200,222],"correct":[80],"response.":[81],"Four":[82],"systems":[83,228],"tested:":[85,205],"Gemma-4B,":[86,123],"Gemma-12B,":[87,128],"Sonnet-5,":[88],"DeepSeek-V4-Flash":[90,186],"(refusal":[91],"conditions":[92],"only).":[93],"Three":[94],"model":[95],"judges":[96],"scored":[97],"majority;":[101],"counted":[104],"only":[105,226],"both":[107,145],"facts":[108,214],"found.":[110],"Results:":[111],"Across":[112],"fixed-corpus":[113],"conditions,":[115],"accuracy":[116,149,206],"ranged":[117],"55.9%":[119],"71.9%":[121],"for":[122,127,133,144],"61.2%":[124],"75.5%":[126],"90.0%":[130],"91.3%":[132],"Sonnet-5.":[134],"Similar":[135],"harder":[139,216],"than":[140,217],"mixed":[141],"candidate":[142,167],"sets":[143,168],"Gemma":[146],"configurations.":[147],"Two-paper":[148],"5.7%,":[151],"17.1%,":[152],"37.8%,":[154],"respectively.":[155],"With":[156],"absent,":[158],"Gemma-12B":[159],"fell":[161,207],"88.3%":[163],"39.9%":[165],"as":[166,208,234],"grew;":[169],"Gemma-4B":[170],"almost":[171],"never":[172],"refused.":[173],"Sonnet-5":[174],"refused":[175,188],"on":[176,191],"94.9%":[177],"sampled":[179,183],"all":[182],"cells.":[185],"also":[187],"frequently,":[189],"but":[190],"80.3%":[192],"matched":[194],"answer-present":[195],"controls.":[196],"Conclusions:":[197],"No":[198],"system":[199],"reliable":[201],"across":[202],"every":[203],"axis":[204],"added,":[212],"interpretation-requiring":[213],"stated":[218],"ones,":[219],"synthesis":[221],"rarely":[223],"achieved,":[224],"some":[227],"recognized":[229],"absent":[230],"evidence.":[231],"What":[232],"counts":[233],"\"successful\"":[235],"literature":[236],"search":[237],"carries":[238],"considerable":[239],"nuance;":[240],"can":[242],"evaluate":[243],"proposed":[244],"tools":[245],"ata":[246],"fine-grained":[247],"level.":[248]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-09-24T00:00:00"}