{"id":"https://openalex.org/W4415311480","doi":"https://doi.org/10.1145/3779211.3795735","title":"InsertRank: LLMs can reason over BM25 scores to Improve Listwise Reranking","display_name":"InsertRank: LLMs can reason over BM25 scores to Improve Listwise Reranking","publication_year":2026,"publication_date":"2026-02-22","ids":{"openalex":"https://openalex.org/W4415311480","doi":"https://doi.org/10.1145/3779211.3795735"},"language":"en","primary_location":{"id":"doi:10.1145/3779211.3795735","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779211.3795735","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3779211.3795735","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Rahul Seetharaman","orcid":"https://orcid.org/0000-0001-6171-4814"},"institutions":[{"id":"https://openalex.org/I177605424","display_name":"Amherst College","ror":"https://ror.org/028vqfs63","country_code":"US","type":"education","lineage":["https://openalex.org/I177605424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahul Seetharaman","raw_affiliation_strings":["University of Massachusetts at Amherst, Amherst, USA"],"raw_orcid":"https://orcid.org/0000-0001-6171-4814","affiliations":[{"raw_affiliation_string":"University of Massachusetts at Amherst, Amherst, USA","institution_ids":["https://openalex.org/I177605424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101721129","display_name":"Aman Bansal","orcid":"https://orcid.org/0000-0001-7771-5459"},"institutions":[{"id":"https://openalex.org/I4210153414","display_name":"Nutanix (United States)","ror":"https://ror.org/04tz2xx73","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153414"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aman Bansal","raw_affiliation_strings":["Core Data Path, Nutanix, San Jose, USA"],"raw_orcid":"https://orcid.org/0009-0003-7967-551X","affiliations":[{"raw_affiliation_string":"Core Data Path, Nutanix, San Jose, USA","institution_ids":["https://openalex.org/I4210153414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120048109","display_name":"Kaustubh D. Dhole","orcid":null},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaustubh Dhole","raw_affiliation_strings":["Department of Computer Science, Emory University, Atlanta, USA"],"raw_orcid":"https://orcid.org/0009-0006-6907-2530","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Emory University, Atlanta, USA","institution_ids":["https://openalex.org/I150468666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"140","last_page":"147"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13417","display_name":"Biomedical Ethics and Regulation","score":0.7102000117301941,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T13417","display_name":"Biomedical Ethics and Regulation","score":0.7102000117301941,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"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/normalization","display_name":"Normalization (sociology)","score":0.5600000023841858},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5508000254631042},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.41260001063346863},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.3831000030040741},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.382099986076355},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.34360000491142273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7123000025749207},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5600000023841858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5562000274658203},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5508000254631042},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5432999730110168},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5041000247001648},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4066999852657318},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3831000030040741},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C62360110","wikidata":"https://www.wikidata.org/wiki/Q96777007","display_name":"Circumscription","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3779211.3795735","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779211.3795735","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.14086","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.14086","pdf_url":"https://arxiv.org/pdf/2506.14086","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.14086","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.14086","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3779211.3795735","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779211.3795735","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4,67],"demonstrated":[5],"significant":[6],"strides":[7],"across":[8,149],"various":[9],"information":[10],"retrieval":[11,49,103,108,126,147],"tasks,":[12],"particularly":[13],"as":[14],"rerankers,":[15],"owing":[16],"to":[17,42,100,236],"their":[18],"strong":[19],"generalization":[20],"and":[21,120,137,141,157,172,198],"knowledgetransfer":[22],"capabilities":[23],"acquired":[24],"from":[25,228],"extensive":[26],"pretraining.":[27],"In":[28,82,181,208],"parallel,":[29],"the":[30,169,175,186,203,213,229],"rise":[31],"of":[32,71,152,166,188,205,215],"LLM-based":[33,89],"chat":[34],"interfaces":[35],"has":[36],"raised":[37],"user":[38],"expectations,":[39],"encouraging":[40],"users":[41],"pose":[43],"more":[44],"complex":[45],"queries":[46],"that":[47,83,91,143],"necessitate":[48],"by":[50],"\"reasoning\"":[51],"over":[52],"documents":[53],"rather":[54],"than":[55],"through":[56],"simple":[57],"keyword":[58],"matching":[59],"or":[60],"semantic":[61],"similarity.":[62],"While":[63],"some":[64],"recent":[65],"efforts":[66],"exploited":[68],"reasoning":[69,114,125],"abilities":[70],"LLMs":[72],"for":[73,79],"reranking":[74,99],"such":[75],"queries,":[76],"considerable":[77],"potential":[78],"improvement":[80],"remains.":[81],"regards,":[84],"we":[85,183,210],"introduce":[86],"InsertRank,":[87],"an":[88,134],"reranker":[90],"leverages":[92],"lexical":[93],"signals":[94],"like":[95,193],"BM25":[96],"scores":[97],"during":[98],"further":[101,201],"improve":[102],"performance.":[104],"InsertRank":[105,144,162,189],"demonstrates":[106],"improved":[107],"effectiveness":[109,148,187,214],"on":[110,168,174,190],"-":[111],"BRIGHT,":[112],"a":[113,122,164,238],"benchmark":[115,127],"spanning":[116,128],"12":[117],"diverse":[118],"domains,":[119],"R2MED,":[121],"specialized":[123],"medical":[124],"8":[129],"different":[130],"tasks.":[131],"We":[132],"conduct":[133],"exhaustive":[135],"evaluation":[136],"several":[138],"ablation":[139],"studies":[140],"demonstrate":[142,185,212],"consistently":[145],"improves":[146],"multiple":[150],"families":[151],"LLMs,":[153],"including":[154,226],"GPT,":[155],"Gemini,":[156],"Deepseek":[158],"models.":[159],"With":[160],"Deepseek-R1,":[161],"achieves":[163],"score":[165],"37.5":[167],"BRIGHT":[170],"benchmark.":[171],"51.1":[173],"R2MED":[176],"benchmark,":[177],"surpassing":[178],"previous":[179],"methods.":[180],"addition,":[182,209],"additionally":[184],"standard":[191],"benchmarks":[192],"TREC":[194,199],"DL":[195],"19,":[196],"20":[197],"HARD,":[200],"demonstrating":[202],"robustness":[204],"this":[206],"method.":[207],"also":[211],"our":[216],"method":[217],"with":[218],"BERT":[219],"based":[220],"retriever":[221,232],"scores,":[222],"thus":[223],"illustrating":[224],"how":[225],"feedback":[227],"first":[230],"stage":[231],"can":[233],"be":[234],"helpful":[235],"guide":[237],"listwise":[239],"LLM":[240],"reranker.":[241]},"counts_by_year":[],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-18T00:00:00"}