{"id":"https://openalex.org/W4416799082","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249099","title":"Enhancing Technical Documents Retrieval for RAG","display_name":"Enhancing Technical Documents Retrieval for RAG","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799082","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249099"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Songjiang Lai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119464","display_name":"Quality and Reliability (Greece)","ror":"https://ror.org/02f8mda22","country_code":"GR","type":"company","lineage":["https://openalex.org/I4210119464"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Songjiang Lai","raw_affiliation_strings":["Centre for Advances in Reliability and Safety,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Advances in Reliability and Safety,Hong Kong,China","institution_ids":["https://openalex.org/I4210119464"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004935515","display_name":"Tsun-Hin Cheung","orcid":"https://orcid.org/0000-0001-5467-6872"},"institutions":[{"id":"https://openalex.org/I4210119464","display_name":"Quality and Reliability (Greece)","ror":"https://ror.org/02f8mda22","country_code":"GR","type":"company","lineage":["https://openalex.org/I4210119464"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Tsun-Hin Cheung","raw_affiliation_strings":["Centre for Advances in Reliability and Safety,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Advances in Reliability and Safety,Hong Kong,China","institution_ids":["https://openalex.org/I4210119464"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ka-Chun Fung","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119464","display_name":"Quality and Reliability (Greece)","ror":"https://ror.org/02f8mda22","country_code":"GR","type":"company","lineage":["https://openalex.org/I4210119464"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Ka-Chun Fung","raw_affiliation_strings":["Centre for Advances in Reliability and Safety,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Advances in Reliability and Safety,Hong Kong,China","institution_ids":["https://openalex.org/I4210119464"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100526741","display_name":"Kaiwen Xue","orcid":"https://orcid.org/0000-0001-8221-5328"},"institutions":[{"id":"https://openalex.org/I4210119464","display_name":"Quality and Reliability (Greece)","ror":"https://ror.org/02f8mda22","country_code":"GR","type":"company","lineage":["https://openalex.org/I4210119464"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Kaiwen Xue","raw_affiliation_strings":["Centre for Advances in Reliability and Safety,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Advances in Reliability and Safety,Hong Kong,China","institution_ids":["https://openalex.org/I4210119464"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087429791","display_name":"Kwan-Ho Lin","orcid":"https://orcid.org/0000-0002-2216-9590"},"institutions":[{"id":"https://openalex.org/I4210119464","display_name":"Quality and Reliability (Greece)","ror":"https://ror.org/02f8mda22","country_code":"GR","type":"company","lineage":["https://openalex.org/I4210119464"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Kwan-Ho Lin","raw_affiliation_strings":["Centre for Advances in Reliability and Safety,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Advances in Reliability and Safety,Hong Kong,China","institution_ids":["https://openalex.org/I4210119464"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101848875","display_name":"Yoojin Choi","orcid":"https://orcid.org/0000-0002-4496-0738"},"institutions":[{"id":"https://openalex.org/I4210119464","display_name":"Quality and Reliability (Greece)","ror":"https://ror.org/02f8mda22","country_code":"GR","type":"company","lineage":["https://openalex.org/I4210119464"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Yan-Ming Choi","raw_affiliation_strings":["Centre for Advances in Reliability and Safety,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Advances in Reliability and Safety,Hong Kong,China","institution_ids":["https://openalex.org/I4210119464"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102732054","display_name":"Vincent Ng","orcid":"https://orcid.org/0000-0001-8237-429X"},"institutions":[{"id":"https://openalex.org/I4210119464","display_name":"Quality and Reliability (Greece)","ror":"https://ror.org/02f8mda22","country_code":"GR","type":"company","lineage":["https://openalex.org/I4210119464"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Vincent Ng","raw_affiliation_strings":["Centre for Advances in Reliability and Safety,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Advances in Reliability and Safety,Hong Kong,China","institution_ids":["https://openalex.org/I4210119464"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019678322","display_name":"Kin\u2010Man Lam","orcid":"https://orcid.org/0000-0002-0422-8454"},"institutions":[{"id":"https://openalex.org/I4210119464","display_name":"Quality and Reliability (Greece)","ror":"https://ror.org/02f8mda22","country_code":"GR","type":"company","lineage":["https://openalex.org/I4210119464"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Kin-Man Lam","raw_affiliation_strings":["Centre for Advances in Reliability and Safety,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Advances in Reliability and Safety,Hong Kong,China","institution_ids":["https://openalex.org/I4210119464"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210119464"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1728918,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1176","last_page":"1181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2863999903202057,"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":0.2863999903202057,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.25189998745918274,"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":0.03799999877810478,"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/automatic-summarization","display_name":"Automatic summarization","score":0.6171000003814697},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5217999815940857},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.447299987077713},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4081000089645386},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.3921999931335449},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.37950000166893005},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.3716000020503998},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.3562000095844269}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8636999726295471},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6171000003814697},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6111000180244446},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5217999815940857},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.447299987077713},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.3921999931335449},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.37950000166893005},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3562000095844269},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.35519999265670776},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.35109999775886536},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2865000069141388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2782999873161316},{"id":"https://openalex.org/C25688753","wikidata":"https://www.wikidata.org/wiki/Q1413406","display_name":"Technical documentation","level":3,"score":0.2718000113964081},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1980867644","https://openalex.org/W2160892561","https://openalex.org/W2970641574","https://openalex.org/W3174544005","https://openalex.org/W4205991051","https://openalex.org/W4252076394","https://openalex.org/W4385188297","https://openalex.org/W4389519448","https://openalex.org/W4400531953","https://openalex.org/W4402335416","https://openalex.org/W4404627005","https://openalex.org/W4409282347"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,47,73,94],"introduce":[4],"Technical-Embeddings,":[5],"a":[6,96],"novel":[7],"framework":[8],"designed":[9],"to":[10,78,112,152],"optimize":[11],"semantic":[12,115],"retrieval":[13,92,180],"in":[14,19,135,158,181],"technical":[15,35,87,159,178],"documentation,":[16],"with":[17],"applications":[18],"both":[20,136],"hardware":[21],"and":[22,32,60,109,126,138,149,156,176,183],"software":[23],"development.":[24],"Our":[25,140],"approach":[26,120],"addresses":[27],"the":[28,39,66,84,143,164],"challenges":[29],"of":[30,41,86,145,166],"understanding":[31],"retrieving":[33],"complex":[34],"content":[36],"by":[37,51],"leveraging":[38],"capabilities":[40],"Large":[42],"Language":[43],"Models":[44],"(LLMs).":[45],"First,":[46],"enhance":[48,91,153],"user":[49,58],"queries":[50,108],"generating":[52],"expanded":[53],"representations":[54],"that":[55,129],"better":[56],"capture":[57,113],"intent":[59],"improve":[61],"dataset":[62],"diversity,":[63],"thereby":[64],"enriching":[65],"fine-tuning":[67],"process":[68],"for":[69,107,174],"embedding":[70],"models.":[71],"Second,":[72],"apply":[74],"summary":[75],"extraction":[76],"techniques":[77],"encode":[79],"essential":[80],"contextual":[81,150],"information,":[82],"refining":[83],"representation":[85],"documents.":[88],"To":[89],"further":[90],"performance,":[93],"fine-tune":[95],"bi-encoder":[97],"BERT":[98],"model":[99],"using":[100],"soft":[101],"prompting,":[102],"incorporating":[103],"separate":[104],"learning":[105],"parameters":[106],"document":[110,179],"context":[111],"fine-grained":[114],"nuances.":[116],"We":[117],"evaluate":[118],"our":[119],"on":[121],"two":[122],"public":[123],"datasets,":[124],"RAG-EDA":[125],"Rust-Docs-QA,":[127],"demonstrating":[128],"Technical-Embeddings":[130],"significantly":[131],"outperforms":[132],"baseline":[133],"models":[134],"precision":[137],"recall.":[139],"findings":[141],"highlight":[142],"effectiveness":[144],"integrating":[146],"query":[147],"expansion":[148],"summarization":[151],"information":[154],"access":[155],"comprehension":[157],"domains.":[160],"This":[161],"work":[162],"advances":[163],"state":[165],"Retrieval-Augmented":[167],"Generation":[168],"(RAG)":[169],"systems,":[170],"offering":[171],"new":[172],"avenues":[173],"efficient":[175],"accurate":[177],"engineering":[182],"product":[184],"development":[185],"workflows.":[186]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}
