{"id":"https://openalex.org/W7168401363","doi":"https://doi.org/10.1145/3805712.3809944","title":"Learning to Reason for Multi-Step Retrieval of Personal Context in Personalized Question Answering","display_name":"Learning to Reason for Multi-Step Retrieval of Personal Context in Personalized Question Answering","publication_year":2026,"publication_date":"2026-07-15","ids":{"openalex":"https://openalex.org/W7168401363","doi":"https://doi.org/10.1145/3805712.3809944"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809944","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809944","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/10.1145/3805712.3809944","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140926765","display_name":"Maryam Amirizaniani","orcid":"https://orcid.org/0000-0002-6142-0637"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maryam Amirizaniani","raw_affiliation_strings":["Information School, University of Washington, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6142-0637","affiliations":[{"raw_affiliation_string":"Information School, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140822635","display_name":"Alireza Salemi","orcid":"https://orcid.org/0009-0006-1937-2615"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alireza Salemi","raw_affiliation_strings":["Center for Intelligent Information Retrieval, University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":"https://orcid.org/0009-0006-1937-2615","affiliations":[{"raw_affiliation_string":"Center for Intelligent Information Retrieval, University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140870383","display_name":"Hamed Zamani","orcid":"https://orcid.org/0000-0002-0800-3340"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hamed Zamani","raw_affiliation_strings":["Center for Intelligent Information Retrieval, University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0800-3340","affiliations":[{"raw_affiliation_string":"Center for Intelligent Information Retrieval, University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]}],"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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3580","last_page":"3586"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6406000256538391},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6046000123023987},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.30720001459121704},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.2849999964237213},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.27639999985694885}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6406000256538391},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6046000123023987},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5092999935150146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3131999969482422},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3091000020503998},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.304500013589859},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2736000120639801},{"id":"https://openalex.org/C3019144022","wikidata":"https://www.wikidata.org/wiki/Q4124998","display_name":"Questions and answers","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.25929999351501465}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3809944","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809944","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:10.1145/3805712.3809944","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809944","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W4368755500","https://openalex.org/W4385569963","https://openalex.org/W4392384703","https://openalex.org/W4400525546","https://openalex.org/W4400526126","https://openalex.org/W4401857375","https://openalex.org/W4402670099","https://openalex.org/W4402671806","https://openalex.org/W4403220350","https://openalex.org/W4403577434","https://openalex.org/W4404781233","https://openalex.org/W4409363267","https://openalex.org/W4411119239","https://openalex.org/W4411119800","https://openalex.org/W4412673539","https://openalex.org/W4412888062","https://openalex.org/W4412944909","https://openalex.org/W4412945610","https://openalex.org/W4415796088","https://openalex.org/W4416016536","https://openalex.org/W4416033577","https://openalex.org/W4416035893","https://openalex.org/W4416035933","https://openalex.org/W4416036988","https://openalex.org/W4416037107","https://openalex.org/W4416078616"],"related_works":[],"abstract_inverted_index":{"Personalization":[0],"in":[1,158],"Question":[2],"Answering":[3],"(QA)":[4],"requires":[5],"answers":[6],"that":[7,30,71,121,145],"are":[8],"both":[9],"accurate":[10],"and":[11,17,53,74,97,127],"aligned":[12],"with":[13,124],"users'":[14],"background,":[15],"preferences,":[16],"historical":[18],"context.":[19],"Existing":[20,42],"state-of-the-art":[21],"methods":[22,43],"primarily":[23],"rely":[24],"on":[25,137],"retrieval-augmented":[26],"generation":[27],"(RAG)":[28],"solutions":[29],"construct":[31],"personal":[32,51,77],"context":[33,78],"by":[34,131],"retrieving":[35],"relevant":[36],"items":[37],"from":[38,76,94],"the":[39,45,116,132,138],"user's":[40,46],"profile.":[41],"use":[44],"query":[47],"directly":[48],"to":[49,58,88,92,99],"retrieve":[50,93],"documents":[52],"such":[54],"strategies":[55],"often":[56],"lead":[57],"surface-level":[59],"personalization.":[60,80],"We":[61],"propose":[62],"PR2":[63,81,146],"(Personalized":[64],"Retrieval-Augmented":[65],"Reasoning),":[66],"a":[67,112],"reinforcement":[68],"learning":[69],"framework":[70,117],"integrates":[72],"reasoning":[73,104,109,119],"retrieval":[75],"for":[79],"learns":[82],"adaptive":[83],"retrieval-reasoning":[84],"policies,":[85],"determining":[86],"when":[87],"retrieve,":[89],"what":[90],"evidence":[91],"user":[95],"profiles,":[96],"how":[98],"incorporate":[100],"it":[101],"into":[102],"intermediate":[103],"steps.":[105],"By":[106],"optimizing":[107],"multi-turn":[108],"trajectories":[110],"under":[111],"personalized":[113,159],"reward":[114,133],"function,":[115],"reinforces":[118],"paths":[120],"better":[122],"align":[123],"user-specific":[125],"preferences":[126],"contextual":[128],"signals":[129],"reflected":[130],"model.":[134],"Extensive":[135],"experiments":[136],"LaMP-QA":[139],"benchmark":[140],"using":[141],"three":[142],"LLMs":[143],"show":[144],"consistently":[147],"outperforms":[148],"strong":[149],"baselines,":[150],"achieving":[151],"an":[152],"average":[153],"relative":[154],"improvement":[155],"of":[156],"8.26%-12.0%":[157],"QA.":[160]},"counts_by_year":[],"updated_date":"2026-07-17T05:52:16.776730","created_date":"2026-07-16T00:00:00"}