{"id":"https://openalex.org/W7157287096","doi":"https://doi.org/10.48550/arxiv.2604.23263","title":"Small Language Model Helps Resolve Semantic Ambiguity of LLM Prompt","display_name":"Small Language Model Helps Resolve Semantic Ambiguity of LLM Prompt","publication_year":2026,"publication_date":"2026-04-25","ids":{"openalex":"https://openalex.org/W7157287096","doi":"https://doi.org/10.48550/arxiv.2604.23263"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.23263","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23263","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2604.23263","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134781215","display_name":"Zhenzhen Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Zhenzhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134819568","display_name":"Chaoning Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Chaoning","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125633009","display_name":"Fachrina Dewi Puspitasari","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Puspitasari, Fachrina Dewi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134810110","display_name":"Jiaquan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jiaquan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133156570","display_name":"Yitian Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yitian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113183905","display_name":"Shuxu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Shuxu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134815896","display_name":"Yang Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yang","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":0.4595000147819519,"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":0.4595000147819519,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.06939999759197235,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.04479999840259552,"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/ambiguity","display_name":"Ambiguity","score":0.7160999774932861},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.628600001335144},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5630999803543091},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5220999717712402},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4659999907016754},{"id":"https://openalex.org/keywords/executor","display_name":"Executor","score":0.42800000309944153},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.42179998755455017},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.38029998540878296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8526999950408936},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.7160999774932861},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.628600001335144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5745000243186951},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5630999803543091},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5220999717712402},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49950000643730164},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4659999907016754},{"id":"https://openalex.org/C180591056","wikidata":"https://www.wikidata.org/wiki/Q654437","display_name":"Executor","level":2,"score":0.42800000309944153},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42179998755455017},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.35569998621940613},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34779998660087585},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C67277372","wikidata":"https://www.wikidata.org/wiki/Q7449085","display_name":"Semantic role labeling","level":3,"score":0.31779998540878296},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C28427503","wikidata":"https://www.wikidata.org/wiki/Q13580300","display_name":"Internal model","level":3,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.23263","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23263","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2604.23263","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23263","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":0.5407949686050415,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1,165],"models":[2,166],"(LLMs)":[3],"are":[4],"increasingly":[5],"utilized":[6],"in":[7,58,110,130],"various":[8],"complex":[9],"reasoning":[10,62,193],"tasks":[11],"due":[12],"to":[13,64,139,156,175],"their":[14,114,178],"excellent":[15],"instruction":[16],"following":[17],"capability.":[18],"However,":[19],"the":[20,27,31,56,60,77,84,88,111,127,140,157,169,218],"model's":[21],"performance":[22,194],"is":[23],"highly":[24],"dependent":[25],"on":[26,184],"open-ended":[28],"characteristics":[29],"of":[30,87,172,201,221],"users'":[32],"input":[33,138],"prompt.":[34],"Natural":[35],"prompts":[36,54],"often":[37],"do":[38],"not":[39],"follow":[40],"proper":[41],"syntactic":[42],"rules,":[43],"which":[44],"creates":[45],"ambiguous":[46,53],"queries":[47],"that":[48,122,189],"yield":[49],"multiple":[50,185],"interpretations.":[51],"Such":[52],"confuse":[55],"model":[57],"choosing":[59],"correct":[61],"paths":[63],"answer":[65],"questions.":[66],"Prior":[67],"works":[68],"address":[69,91],"this":[70,92],"challenge":[71],"by":[72,195],"applying":[73],"query":[74],"editing":[75],"during":[76],"LLM":[78,222],"inference":[79],"process":[80],"without":[81,216],"explicitly":[82,143],"solving":[83],"root":[85],"cause":[86],"ambiguity.":[89],"To":[90],"limitation,":[93],"we":[94,106,125,187],"propose":[95],"a":[96,131,136,151,199],"pre-inference":[97],"prompt":[98,103,173,208,213],"optimization":[99,214],"mechanism":[100,220],"via":[101],"explicit":[102,207],"disambiguation.":[104],"Particularly,":[105],"identify":[107],"semantic":[108,120,145],"risks":[109],"prompt,":[112],"check":[113],"multi-perspective":[115],"consistency,":[116],"and":[117],"resolve":[118],"any":[119],"conflicts":[121],"arise.":[123],"Finally,":[124],"organize":[126],"resolved":[128],"ambiguities":[129],"logically":[132],"structured":[133],"manner":[134],"as":[135,168,210],"clean":[137],"LLM.":[141],"By":[142],"resolving":[144],"ambiguity,":[146],"our":[147,190],"method":[148,191,215],"can":[149],"produce":[150],"more":[152],"focused":[153],"attention":[154],"distribution":[155],"semantically":[158],"essential":[159],"tokens.":[160],"We":[161],"also":[162],"leverage":[163],"small":[164],"(SLMs)":[167],"main":[170],"executor":[171],"disambiguation":[174,209],"benefit":[176],"from":[177],"efficient":[179],"computation.":[180],"Through":[181],"comprehensive":[182],"experiments":[183],"benchmarks,":[186],"demonstrate":[188],"improves":[192],"2.5":[196],"points":[197],"at":[198],"cost":[200],"only":[202],"\\$0.02.":[203],"Our":[204],"study":[205],"promotes":[206],"an":[211],"effective":[212],"disturbing":[217],"internal":[219],"inference.":[223]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-29T00:00:00"}