{"id":"https://openalex.org/W7167929854","doi":"https://doi.org/10.1145/3805712.3809747","title":"Learning from Natural Language Feedback for Personalized Question Answering","display_name":"Learning from Natural Language Feedback for Personalized Question Answering","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167929854","doi":"https://doi.org/10.1145/3805712.3809747"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809747","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809747","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/10.1145/3805712.3809747","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082594835","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/A5101457713","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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24603500"],"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":"1554","last_page":"1565"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8015000224113464,"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":0.8015000224113464,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.06629999727010727,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.03009999915957451,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.879800021648407},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.593500018119812},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.566100001335144},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5461000204086304},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5444999933242798},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.5418000221252441},{"id":"https://openalex.org/keywords/user-modeling","display_name":"User modeling","score":0.42910000681877136},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41920000314712524}],"concepts":[{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.879800021648407},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7817000150680542},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.593500018119812},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.566100001335144},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5461000204086304},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5444999933242798},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.5418000221252441},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47029998898506165},{"id":"https://openalex.org/C67712803","wikidata":"https://www.wikidata.org/wiki/Q7901853","display_name":"User modeling","level":3,"score":0.42910000681877136},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C142039133","wikidata":"https://www.wikidata.org/wiki/Q3620943","display_name":"Personalized learning","level":5,"score":0.3862000107765198},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3578999936580658},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35350000858306885},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3393999934196472},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C3017893058","wikidata":"https://www.wikidata.org/wiki/Q999278","display_name":"User satisfaction","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2558000087738037},{"id":"https://openalex.org/C2779305910","wikidata":"https://www.wikidata.org/wiki/Q5172809","display_name":"Corrective feedback","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3809747","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809747","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:10.1145/3805712.3809747","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809747","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":[{"display_name":"Quality Education","score":0.7463120222091675,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2051780479","https://openalex.org/W2076006872","https://openalex.org/W2168717408","https://openalex.org/W3190590916","https://openalex.org/W4384822171","https://openalex.org/W4385572146","https://openalex.org/W4396723585","https://openalex.org/W4400525546","https://openalex.org/W4401042327","https://openalex.org/W4401042391","https://openalex.org/W4402671806","https://openalex.org/W4408612787","https://openalex.org/W4411630224","https://openalex.org/W4412673541","https://openalex.org/W4412945169","https://openalex.org/W4412945696","https://openalex.org/W4416037107","https://openalex.org/W7133208539"],"related_works":[],"abstract_inverted_index":{"Personalization":[0],"is":[1],"crucial":[2],"for":[3,23,75,191],"enhancing":[4],"both":[5],"the":[6,93,97,110,127,132,136,153,168,175,179],"effectiveness":[7],"and":[8,66,96,105,118,130,164],"user":[9,94],"satisfaction":[10],"of":[11,158,178],"language":[12,26,85],"technologies,":[13],"particularly":[14],"in":[15,140],"information-seeking":[16],"tasks":[17],"like":[18],"question":[19,98,194],"answering.":[20,195],"Current":[21],"approaches":[22],"personalizing":[24],"large":[25],"models":[27,45],"(LLMs)":[28],"often":[29],"rely":[30],"on":[31,92,135,152],"retrieval-augmented":[32],"generation":[33,78],"(RAG),":[34],"followed":[35],"by":[36],"reinforcement":[37],"learning":[38,64],"with":[39,83],"scalar":[40,56,81],"reward":[41],"signals":[42,190],"to":[43,47,113],"teach":[44],"how":[46],"use":[48],"retrieved":[49],"personal":[50],"context.":[51],"We":[52,69],"believe":[53],"that":[54,79,88,144,156,185],"these":[55],"rewards":[57,82],"sometimes":[58],"provide":[59],"weak,":[60],"non-instructive":[61],"feedback,":[62],"limiting":[63],"efficiency":[65],"personalization":[67,121],"quality.":[68],"introduce":[70],"VAC,":[71],"a":[72,103,141],"novel":[73],"framework":[74],"personalized":[76,193],"response":[77],"replaces":[80],"natural":[84],"feedback":[86,128,148],"(NLF)":[87],"are":[89],"generated":[90,180],"conditioned":[91],"profiles":[95],"narratives.":[99],"NLF":[100,186],"serves":[101],"as":[102],"rich":[104],"actionable":[106],"supervision":[107],"signal,":[108],"allowing":[109],"policy":[111,133,142],"model":[112,129,134,143],"iteratively":[114],"refine":[115],"its":[116],"outputs":[117],"internalize":[119],"effective":[120,189],"strategies.":[122],"Training":[123],"alternates":[124],"between":[125],"optimizing":[126,192],"fine-tuning":[131],"improved":[137],"responses,":[138],"resulting":[139],"no":[145],"longer":[146],"requires":[147],"at":[149],"inference.":[150],"Evaluation":[151],"LaMP-QA":[154],"benchmark":[155],"consists":[157],"three":[159],"diverse":[160],"domains":[161],"demonstrates":[162],"consistent":[163],"significant":[165],"improvements":[166],"over":[167],"state-of-the-art":[169],"results.":[170],"Human":[171],"evaluations":[172],"further":[173],"confirm":[174],"superior":[176],"quality":[177],"responses.":[181],"These":[182],"results":[183],"demonstrate":[184],"provides":[187],"more":[188]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-11T00:00:00"}