{"id":"https://openalex.org/W7128399116","doi":"https://doi.org/10.48550/arxiv.2602.06526","title":"Completing Missing Annotation: Multi-Agent Debate for Accurate and Scalable Relevant Assessment for IR Benchmarks","display_name":"Completing Missing Annotation: Multi-Agent Debate for Accurate and Scalable Relevant Assessment for IR Benchmarks","publication_year":2026,"publication_date":"2026-02-06","ids":{"openalex":"https://openalex.org/W7128399116","doi":"https://doi.org/10.48550/arxiv.2602.06526"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.06526","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.06526","pdf_url":"https://arxiv.org/pdf/2602.06526","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.06526","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119204494","display_name":"Minjeong Ban","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ban, Minjeong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125412705","display_name":"Jeonghwan Choi","orcid":"https://orcid.org/0009-0002-6802-3009","observed_orcids":["https://orcid.org/0009-0002-6802-3009"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Choi, Jeonghwan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076598577","display_name":"Hyangsuk Min","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min, Hyangsuk","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125402698","display_name":"Nicole Hee-Yeon Kim","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Nicole Hee-Yeon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099054888","display_name":"Minseok Kim","orcid":"https://orcid.org/0000-0002-3864-8190","observed_orcids":["https://orcid.org/0000-0002-3864-8190"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Minseok","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112008082","display_name":"Jae-Gil Lee","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Jae-Gil","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125420089","display_name":"Hwanjun Song","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Hwanjun","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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9990000128746033,"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":0.9990000128746033,"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/T10028","display_name":"Topic Modeling","score":0.0006000000284984708,"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/T10203","display_name":"Recommender Systems and Techniques","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/information-retrieval-evaluation","display_name":"information retrieval evaluation","score":0.8050000071525574},{"id":"https://openalex.org/keywords/missing-annotations","display_name":"missing annotations","score":0.47200000286102295},{"id":"https://openalex.org/keywords/relevance-assessment","display_name":"relevance assessment","score":0.8370000123977661},{"id":"https://openalex.org/keywords/multi-agent-debate","display_name":"multi-agent debate","score":0.9290000200271606},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.8289999961853027},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.7649999856948853},{"id":"https://openalex.org/keywords/assessment-bias","display_name":"evaluation bias","score":0.7450000047683716},{"id":"https://openalex.org/keywords/dreams","display_name":"dreams","score":0.7200000286102295}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7437999844551086},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6996999979019165},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6912999749183655},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5198000073432922},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5177000164985657},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5169000029563904},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5016999840736389},{"id":"https://openalex.org/C51110983","wikidata":"https://www.wikidata.org/wiki/Q16503490","display_name":"Overconfidence effect","level":2,"score":0.47040000557899475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42080000042915344},{"id":"https://openalex.org/C2777742833","wikidata":"https://www.wikidata.org/wiki/Q1964083","display_name":"Reciprocal","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3434999883174896},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.28519999980926514},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.06526","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.06526","pdf_url":"https://arxiv.org/pdf/2602.06526","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2602.06526","doi":"https://doi.org/10.48550/arxiv.2602.06526","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.06526","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.06526","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.06526","pdf_url":"https://arxiv.org/pdf/2602.06526","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416018015","https://openalex.org/W4407780254","https://openalex.org/W4412673538","https://openalex.org/W7213789251","https://openalex.org/W4412377345","https://openalex.org/W4400374549","https://openalex.org/W7119235771","https://openalex.org/W4403995465","https://openalex.org/W7168349165","https://openalex.org/W4396816204"],"abstract_inverted_index":{"Information":[0],"retrieval":[1],"(IR)":[2],"evaluation":[3,100,120],"remains":[4],"challenging":[5],"due":[6],"to":[7,30,121],"incomplete":[8],"IR":[9,116],"benchmark":[10,97],"datasets":[11],"that":[12,98,124],"contain":[13],"unlabeled":[14],"relevant":[15,111],"chunks.":[16,112],"While":[17],"LLMs":[18],"and":[19,33,57,73,102,118,146],"LLM-human":[20],"hybrid":[21],"strategies":[22],"reduce":[23],"costly":[24],"human":[25,88],"effort,":[26],"they":[27],"remain":[28],"prone":[29],"LLM":[31,50],"overconfidence":[32],"ineffective":[34],"AI-to-human":[35,76],"escalation.":[36],"To":[37],"address":[38],"this,":[39],"we":[40,92],"propose":[41],"DREAM,":[42,91],"a":[43,95],"multi-round":[44],"debate-based":[45],"relevance":[46,138],"assessment":[47,139],"framework":[48,140],"with":[49,85],"agents,":[51],"built":[52],"on":[53],"opposing":[54],"initial":[55],"stances":[56],"iterative":[58],"reciprocal":[59],"critique.":[60],"Through":[61],"our":[62],"agreement-based":[63],"debate,":[64],"it":[65],"yields":[66],"more":[67,74],"accurate":[68],"labeling":[69,83],"for":[70,78],"certain":[71],"cases":[72],"reliable":[75],"escalation":[77],"uncertain":[79],"ones,":[80],"achieving":[81],"95.2%":[82],"accuracy":[84],"only":[86,128],"3.5%":[87],"involvement.":[89],"Using":[90],"build":[93],"BRIDGE,":[94],"refined":[96],"mitigates":[99],"bias":[101],"enables":[103],"fairer":[104],"retriever":[105,130],"comparison":[106],"by":[107],"uncovering":[108],"29,824":[109],"missing":[110],"We":[113],"then":[114],"re-benchmark":[115],"systems":[117],"extend":[119],"RAG,":[122],"showing":[123],"unaddressed":[125],"holes":[126],"not":[127],"distort":[129],"rankings":[131],"but":[132],"also":[133],"drive":[134],"retrieval-generation":[135],"misalignment.":[136],"The":[137],"is":[141,150],"available":[142,151],"at":[143,152],"https:":[144],"//github.com/DISL-Lab/DREAM-ICLR-26;":[145],"the":[147],"BRIDGE":[148],"dataset":[149],"https://github.com/DISL-Lab/BRIDGE-Benchmark.":[153]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-10T00:00:00"}