{"id":"https://openalex.org/W7167901679","doi":"https://doi.org/10.1145/3805712.3809981","title":"Too Many Questions: Deriving Concise and Effective Nugget Banks","display_name":"Too Many Questions: Deriving Concise and Effective Nugget Banks","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167901679","doi":"https://doi.org/10.1145/3805712.3809981"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809981","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809981","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809981","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027260515","display_name":"Laura Dietz","orcid":"https://orcid.org/0000-0003-1624-3907"},"institutions":[{"id":"https://openalex.org/I161057412","display_name":"University of New Hampshire","ror":"https://ror.org/01rmh9n78","country_code":"US","type":"education","lineage":["https://openalex.org/I161057412"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laura Dietz","raw_affiliation_strings":["University of New Hampshire, Durham, New Hampshire, USA"],"raw_orcid":"https://orcid.org/0000-0003-1624-3907","affiliations":[{"raw_affiliation_string":"University of New Hampshire, Durham, New Hampshire, USA","institution_ids":["https://openalex.org/I161057412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093854193","display_name":"Naghmeh Farzi","orcid":null},"institutions":[{"id":"https://openalex.org/I161057412","display_name":"University of New Hampshire","ror":"https://ror.org/01rmh9n78","country_code":"US","type":"education","lineage":["https://openalex.org/I161057412"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naghmeh Farzi","raw_affiliation_strings":["University of New Hampshire, Durham, New Hampshire, USA"],"raw_orcid":"https://orcid.org/0009-0000-3297-8888","affiliations":[{"raw_affiliation_string":"University of New Hampshire, Durham, New Hampshire, USA","institution_ids":["https://openalex.org/I161057412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062016266","display_name":"Eugene Yang","orcid":"https://orcid.org/0000-0002-0051-1535"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Yang","raw_affiliation_strings":["Johns Hopkins University, Baltimore, Maryland, USA"],"raw_orcid":"https://orcid.org/0000-0002-0051-1535","affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, Maryland, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037074105","display_name":"Dawn Lawrie","orcid":"https://orcid.org/0000-0001-7347-7086"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dawn Lawrie","raw_affiliation_strings":["Johns Hopkins University, Baltimore, Maryland, USA"],"raw_orcid":"https://orcid.org/0000-0001-7347-7086","affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, Maryland, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3688","last_page":"3693"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6358000040054321,"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":0.6358000040054321,"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":0.0608999989926815,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.03400000184774399,"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/scalability","display_name":"Scalability","score":0.6050000190734863},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.51910001039505},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4862000048160553},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.41130000352859497},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.41110000014305115}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6050000190734863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5335999727249146},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.51910001039505},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4862000048160553},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.41130000352859497},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.41110000014305115},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.301800012588501},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.24079999327659607}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3809981","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809981","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809981","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809981","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6651175618171692,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2017633929","https://openalex.org/W3159852056","https://openalex.org/W4389519598","https://openalex.org/W4396812188","https://openalex.org/W4401330297","https://openalex.org/W4411630045","https://openalex.org/W4412376941","https://openalex.org/W4412377058","https://openalex.org/W7133239970","https://openalex.org/W7140214537","https://openalex.org/W7168423013"],"related_works":[],"abstract_inverted_index":{"Nugget-based":[0],"LLM":[1,37,126],"judges":[2],"evaluate":[3],"Retrieval-Augmented":[4],"Generation":[5],"(RAG)":[6],"systems":[7],"using":[8],"a":[9,31,62,116],"bank":[10,57],"of":[11,33,65,105,119,125,155],"questions":[12,73,120],"that":[13,71,149,180],"capture":[14],"the":[15,48,55,103,123],"key":[16],"facts":[17],"and":[18,36,52,77,157,184],"criteria":[19],"an":[20,100,163],"answer":[21],"should":[22,58],"address.":[23],"These":[24],"nugget":[25,56,67,114,178],"banks":[26,179],"are":[27,41,74,181],"typically":[28,97],"constructed":[29],"through":[30],"combination":[32],"human":[34],"input":[35],"generation.":[38],"System":[39],"outputs":[40],"graded":[42,111],"by":[43,135],"how":[44,169],"well":[45],"they":[46],"cover":[47],"nuggets.":[49],"For":[50],"cost":[51],"scalability":[53],"reasons,":[54],"be":[59,174],"small.":[60],"However,":[61],"major":[63],"limitation":[64],"current":[66],"generation":[68],"approaches":[69],"is":[70,110],"many":[72],"overly":[75],"generic":[76],"fail":[78],"to":[79,99,132,176],"discriminate":[80],"between":[81,160],"top-performing":[82,190],"RAG":[83,191],"systems.":[84,192],"Grounding":[85],"nuggets":[86,141],"in":[87,102,152],"system":[88],"responses":[89,161],"or":[90],"source":[91],"documents":[92],"can":[93,173],"increase":[94],"specificity,":[95],"but":[96],"leads":[98],"explosion":[101],"number":[104,118],"questions.":[106],"Since":[107],"every":[108,113],"response":[109],"for":[112],"question,":[115],"higher":[117],"directly":[121],"increases":[122],"amount":[124],"prompts":[127],"and/or":[128],"tokens":[129],"required,":[130],"contributing":[131],"costs.":[133],"Inspired":[134],"preference-based":[136],"evaluation,":[137],"we":[138],"derive":[139],"differential":[140],"from":[142],"winner-loser":[143],"passage":[144],"pairs,":[145],"focusing":[146],"on":[147],"information":[148],"captures":[150],"differences":[151],"topicality,":[153],"level":[154],"detail,":[156],"evidential":[158],"support":[159],"under":[162],"automatic":[164],"preference":[165],"judge.":[166],"We":[167],"examine":[168],"these":[170],"contrastive":[171],"signals":[172],"leveraged":[175],"construct":[177],"both":[182],"compact":[183],"discriminative,":[185],"enabling":[186],"reliable":[187],"separation":[188],"among":[189]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2026-07-11T00:00:00"}