{"id":"https://openalex.org/W7162469413","doi":"https://doi.org/10.48550/arxiv.2605.25039","title":"AstroRAG -- A Pagerank-Based Retrieval-Augmented Generation Pipeline for Question Answering in Astronomy","display_name":"AstroRAG -- A Pagerank-Based Retrieval-Augmented Generation Pipeline for Question Answering in Astronomy","publication_year":2026,"publication_date":"2026-05-24","ids":{"openalex":"https://openalex.org/W7162469413","doi":"https://doi.org/10.48550/arxiv.2605.25039"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.25039","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25039","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.2605.25039","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136999839","display_name":"Zhifeng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhifeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075957214","display_name":"Jason Jingshi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jason Jingshi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137047216","display_name":"Kaihao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Kaihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137067213","display_name":"Ramesh Sankaranarayana","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sankaranarayana, Ramesh","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":0.43950000405311584,"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":0.43950000405311584,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.13439999520778656,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.10570000112056732,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7299000024795532},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6445000171661377},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5002999901771545},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.4900999963283539},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.47620001435279846},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.43160000443458557},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.39899998903274536},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3978999853134155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7570000290870667},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7299000024795532},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6445000171661377},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5002999901771545},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.4900999963283539},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47130000591278076},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.43160000443458557},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3944000005722046},{"id":"https://openalex.org/C2779172887","wikidata":"https://www.wikidata.org/wiki/Q184316","display_name":"PageRank","level":2,"score":0.392300009727478},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33009999990463257},{"id":"https://openalex.org/C80156102","wikidata":"https://www.wikidata.org/wiki/Q788036","display_name":"Resolver","level":3,"score":0.31790000200271606},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C144559511","wikidata":"https://www.wikidata.org/wiki/Q2986279","display_name":"Principal (computer security)","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2711000144481659},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26820001006126404},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.25039","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25039","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.2605.25039","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25039","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":0.44666507840156555,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1,9],"models":[2],"(LLMs)":[3],"demonstrate":[4,147],"strong":[5],"performance":[6,149,168],"in":[7,31,63,74,183],"natural":[8],"processing":[10],"but":[11],"often":[12],"generate":[13],"factual":[14],"errors":[15,27],"when":[16],"relying":[17],"solely":[18],"on":[19,100,139],"parametric":[20],"knowledge.":[21],"Retrieval-Augmented":[22],"Generation":[23],"(RAG)":[24,57],"mitigates":[25],"these":[26],"by":[28],"grounding":[29],"responses":[30],"external":[32],"evidence,":[33],"yet":[34],"conventional":[35],"retrieve-and-dump":[36],"approaches":[37],"frequently":[38],"introduce":[39],"irrelevant":[40],"context":[41,110],"that":[42],"degrades":[43],"answer":[44],"quality.":[45],"In":[46,154],"this":[47],"work,":[48],"we":[49],"present":[50],"AstroRAG":[51],"--":[52],"a":[53,78,88,95,101,106,112,188],"PageRank-based":[54],"retrieval-augmented":[55],"generation":[56],"pipeline":[58,138],"adapted":[59],"for":[60,143,191],"question":[61],"answering":[62],"astronomy.":[64],"The":[65],"system":[66],"performs":[67],"token-aware":[68],"chunking":[69],"and":[70,93,121,146,162,181],"per-instance,":[71],"ephemeral":[72],"indexing":[73,130],"Elasticsearch,":[75],"then":[76],"executes":[77],"two-stage":[79],"retrieval:":[80],"(i)":[81],"Maximal":[82],"Marginal":[83],"Relevance":[84],"(MMR)":[85],"to":[86,104,131,194],"obtain":[87],"small,":[89],"diverse":[90],"candidate":[91],"set":[92],"(ii)":[94],"reader-driven":[96],"PageRank":[97],"(PR)":[98],"re-ranking":[99],"similarity":[102],"graph":[103],"identify":[105],"compact,":[107],"mutually":[108],"supportive":[109],"under":[111],"strict":[113],"token":[114],"budget.":[115],"Our":[116],"design":[117],"is":[118,126],"training-free,":[119],"privacy-preserving,":[120],"reproducible,":[122],"as":[123],"each":[124],"instance":[125],"processed":[127],"through":[128],"transient":[129],"prevent":[132],"cross-task":[133],"leakage.":[134],"We":[135],"evaluate":[136],"the":[137,140,156,167,176],"AstroQA":[141],"benchmark":[142],"astronomy":[144],"QA,":[145],"competitive":[148],"across":[150],"all":[151],"difficulty":[152],"levels.":[153],"particular,":[155],"RAG-enhanced":[157],"Mistral-7B":[158],"achieves":[159],"\\textbf{79.49\\%":[160,163],"accuracy}":[161],"F1-score},":[164],"nearly":[165],"doubling":[166],"of":[169,178],"its":[170],"non-RAG":[171],"counterpart.":[172],"These":[173],"results":[174],"highlight":[175],"effectiveness":[177],"disciplined":[179],"retrieval":[180],"refinement":[182],"boosting":[184],"domain-specific":[185],"reasoning,":[186],"establishing":[187],"robust":[189],"foundation":[190],"extending":[192],"RAG":[193],"other":[195],"scientific":[196],"fields.":[197]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-27T00:00:00"}