{"id":"https://openalex.org/W7166682611","doi":"https://doi.org/10.48550/arxiv.2606.29706","title":"ARMOR: Adaptive Retriever Optimization for Low-Resource Telecom Question Answering","display_name":"ARMOR: Adaptive Retriever Optimization for Low-Resource Telecom Question Answering","publication_year":2026,"publication_date":"2026-06-29","ids":{"openalex":"https://openalex.org/W7166682611","doi":"https://doi.org/10.48550/arxiv.2606.29706"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.29706","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29706","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,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.29706","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136166088","display_name":"Heshan Fernando","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fernando, Heshan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101535527","display_name":"Quan Xiao","orcid":"https://orcid.org/0009-0008-8492-0037"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Quan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139672425","display_name":"Yan Xin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin, Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050105433","display_name":"T X Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Tianyi","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/T10028","display_name":"Topic Modeling","score":0.5105000138282776,"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":0.5105000138282776,"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":0.24130000174045563,"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":0.15209999680519104,"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/leverage","display_name":"Leverage (statistics)","score":0.6011000275611877},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5637999773025513},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.5049999952316284},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.420199990272522},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.3424000144004822},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.3391999900341034},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.33550000190734863},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.32739999890327454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7522000074386597},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6011000275611877},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5637999773025513},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5356000065803528},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.5049999952316284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4271000027656555},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.420199990272522},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.3391999900341034},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3278999924659729},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31189998984336853},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.2865999937057495},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.29706","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29706","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,"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:10.48550/arxiv.2606.29706","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29706","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,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.41118112206459045,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Telecom":[0],"question":[1],"answering":[2],"(QA)":[3],"is":[4,13,111,212],"a":[5,59,88,100,144],"challenging":[6],"setting":[7],"for":[8,164,170],"retrieval-augmented":[9],"generation":[10,126,206],"(RAG):":[11],"evidence":[12,202],"fragmented":[14],"across":[15],"standards,":[16],"papers,":[17],"encyclopedic":[18],"resources,":[19],"and":[20,23,31,42,68,93,128,139,175,178,193,204],"web":[21],"documents,":[22],"answers":[24],"often":[25],"hinge":[26],"on":[27],"technical":[28],"tables,":[29],"equations,":[30],"specialized":[32],"protocol":[33],"language.":[34],"In":[35],"low-resource":[36],"subdomains,":[37],"generator":[38,81],"fine-tuning":[39,106],"can":[40,64,98],"over-specialize":[41],"degrade":[43],"general":[44],"capability,":[45],"making":[46],"query-side":[47],"retriever":[48,70,145],"adaptation":[49,85],"an":[50],"attractive":[51],"alternative.":[52],"To":[53],"this":[54],"end,":[55],"we":[56,157,197],"ask":[57],"whether":[58],"fixed-generator,":[60],"query-adapted":[61],"RAG":[62,122,172],"system":[63],"outperform":[65],"generator-side":[66],"adaptation,":[67],"which":[69,124,133,166],"objectives":[71,118],"best":[72],"support":[73],"that":[74,199],"setting.":[75],"We":[76,113],"motivate":[77],"retrieval,":[78],"rather":[79],"than":[80,104],"fine-tuning,":[82],"as":[83],"the":[84,120,129,153,171,180,185],"target":[86],"through":[87,143],"capacity":[89],"comparison:":[90],"under":[91],"bounded-parameter":[92],"soft-retrieval":[94],"assumptions,":[95],"query-encoder":[96],"tuning":[97],"have":[99],"smaller":[101],"estimation":[102],"term":[103],"supervised":[105],"when":[107],"its":[108],"effective":[109],"dimension":[110],"smaller.":[112],"identify":[114],"two":[115],"particularly":[116],"relevant":[117],"--":[119,138],"latent-document":[121],"likelihood,":[123],"optimizes":[125],"utility,":[127],"InfoNCE":[130,176],"contrastive":[131],"objective,":[132],"improves":[134,201],"semantic":[135],"retrieval":[136,173,192,203],"geometry":[137],"leverage":[140],"them":[141],"jointly":[142],"optimization":[146],"method":[147],"targeting":[148],"downstream":[149],"QA":[150,195],"performance":[151],"in":[152,207],"telecom":[154],"domain.":[155],"Specifically,":[156],"introduce":[158],"ARMOR,":[159],"Adaptive":[160],"Regularized":[161],"Mixture":[162],"Optimization":[163],"Retrievers,":[165],"learns":[167],"separate":[168],"temperatures":[169],"distribution":[174],"softmax":[177],"regularizes":[179],"adapted":[181],"query":[182,188],"encoder":[183],"toward":[184],"frozen":[186],"base":[187],"encoder.":[189],"Across":[190],"telecom-specific":[191],"generative":[194],"benchmarks,":[196],"show":[198],"ARMOR":[200],"answer":[205],"several":[208],"in-domain":[209],"settings.":[210],"Code":[211],"available":[213],"at":[214],"https://github.com/heshandevaka/ARMOR.git.":[215]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-01T00:00:00"}