{"id":"https://openalex.org/W7160908039","doi":"https://doi.org/10.48550/arxiv.2605.09304","title":"Generating Complex Code Analyzers from Natural Language Questions","display_name":"Generating Complex Code Analyzers from Natural Language Questions","publication_year":2026,"publication_date":"2026-05-10","ids":{"openalex":"https://openalex.org/W7160908039","doi":"https://doi.org/10.48550/arxiv.2605.09304"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2605.09304","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.09304","pdf_url":"https://arxiv.org/pdf/2605.09304","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2605.09304","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101891067","display_name":"Amirmohammad Nazari","orcid":"https://orcid.org/0009-0000-5675-247X","observed_orcids":["https://orcid.org/0009-0000-5675-247X","https://orcid.org/0009-0005-6529-9124"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nazari, Amirmohammad","raw_affiliation_strings":["University of Southern California Los Angeles , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California Los Angeles , CA , USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082544624","display_name":"Sadra Sabouri","orcid":"https://orcid.org/0000-0003-1047-2346","observed_orcids":["https://orcid.org/0000-0003-1047-2346"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sabouri, Sadra","raw_affiliation_strings":["University of Southern California Los Angeles , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California Los Angeles , CA , USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112120097","display_name":"Wang Zhu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Wang Bill","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041906762","display_name":"Robin Jia","orcid":"https://orcid.org/0009-0002-8123-7132","observed_orcids":["https://orcid.org/0009-0002-8123-7132"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jia, Robin","raw_affiliation_strings":["University of Southern California Los Angeles , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California Los Angeles , CA , USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059243154","display_name":"Souti Chattopadhyay","orcid":"https://orcid.org/0000-0003-1644-7344","observed_orcids":["https://orcid.org/0000-0003-1644-7344"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chattopadhyay, Souti","raw_affiliation_strings":["University of Southern California Los Angeles , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California Los Angeles , CA , USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024988696","display_name":"Mukund Raghothaman","orcid":"https://orcid.org/0000-0003-2879-0932","observed_orcids":["https://orcid.org/0000-0003-2879-0932"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raghothaman, Mukund","raw_affiliation_strings":["University of Southern California Los Angeles , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California Los Angeles , CA , USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10260","display_name":"Software Engineering Research","score":0.9916999936103821,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9916999936103821,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.007899999618530273,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10430","display_name":"Software Engineering Techniques and Practices","score":9.999999747378752e-05,"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/codeql","display_name":"CodeQL","score":0.640999972820282},{"id":"https://openalex.org/keywords/query-generation","display_name":"query generation","score":0.6859999895095825},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8849999904632568},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.8820000290870667},{"id":"https://openalex.org/keywords/query-debugging","display_name":"query debugging","score":0.7289999723434448},{"id":"https://openalex.org/keywords/self-testing","display_name":"self-testing","score":0.5789999961853027},{"id":"https://openalex.org/keywords/bug-finding","display_name":"bug detection","score":0.6039999723434448},{"id":"https://openalex.org/keywords/program-analysis","display_name":"program analysis","score":0.4569999873638153},{"id":"https://openalex.org/keywords/merlin","display_name":"Merlin","score":0.3779999911785126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8985999822616577},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.6507999897003174},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6241000294685364},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5863000154495239},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48590001463890076},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4708000123500824},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46810001134872437},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4392000138759613},{"id":"https://openalex.org/C144559511","wikidata":"https://www.wikidata.org/wiki/Q2986279","display_name":"Principal (computer security)","level":2,"score":0.4390999972820282},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4368000030517578},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4343999922275543},{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.4244000017642975},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4196999967098236},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3605000078678131},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.35100001096725464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34119999408721924},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3028999865055084},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.26260000467300415}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2605.09304","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.09304","pdf_url":"https://arxiv.org/pdf/2605.09304","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2605.09304","doi":"https://doi.org/10.48550/arxiv.2605.09304","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.09304","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2605.09304","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.09304","pdf_url":"https://arxiv.org/pdf/2605.09304","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7160908039.pdf","grobid_xml":"https://content.openalex.org/works/W7160908039.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391912518","https://openalex.org/W7160542389","https://openalex.org/W4403854137","https://openalex.org/W7164375192","https://openalex.org/W4408722075","https://openalex.org/W4416167123","https://openalex.org/W4415795198","https://openalex.org/W4415746206","https://openalex.org/W4416156915","https://openalex.org/W4407551092"],"abstract_inverted_index":{"Many":[0],"software":[1,217],"development":[2],"tasks,":[3,209],"such":[4,109],"as":[5,120,145],"implementing":[6],"features":[7],"and":[8,49,61,117,160,182,195,251],"fixing":[9],"bugs,":[10],"begin":[11],"with":[12,55,87],"developers":[13],"posing":[14],"questions":[15,21,43,76,204],"about":[16,22,81],"a":[17,70,89,121,155,161,199,233],"codebase.":[18],"However,":[19],"answering":[20,74],"codebases":[23,57],"that":[24,77,93,180,226,239],"span":[25],"millions":[26],"of":[27,29,33,108,143,173,201,216,249],"lines":[28],"code":[30],"across":[31],"thousands":[32],"files":[34],"is":[35],"non-trivial.":[36],"Standard":[37],"tools":[38],"like":[39],"grep":[40],"cannot":[41],"answer":[42],"requiring":[44],"semantic":[45,184],"or":[46],"inter-procedural":[47],"reasoning,":[48],"large":[50,56,98],"language":[51,203],"models":[52],"(LLMs)":[53],"struggle":[54],"due":[58],"to":[59,241,258],"resource":[60],"context":[62],"constraints.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67,237],"present":[68],"Merlin,":[69],"new":[71],"system":[72],"for":[73,256],"free-form":[75],"require":[78],"analytical":[79],"reasoning":[80],"code.":[82],"Merlin":[83,191,210,242],"integrates":[84],"an":[85,247],"LLM":[86],"CodeQL,":[88],"program":[90,112],"analysis":[91,113],"framework":[92],"supports":[94],"expressive":[95],"queries":[96,114,126,135],"over":[97],"codebases.":[99],"We":[100,149,189],"face":[101],"two":[102],"principal":[103],"challenges":[104,152],"in":[105,186],"the":[106,140,171,214,254],"design":[107],"systems:":[110],"First,":[111],"are":[115,136],"diverse":[116],"semantically":[118],"complex;":[119],"result,":[122],"even":[123],"syntactically":[124],"well-formed":[125],"frequently":[127],"produce":[128],"degenerate/empty":[129],"results.":[130],"Furthermore,":[131],"relatively":[132],"few":[133],"CodeQL":[134,146],"available":[137],"online,":[138],"limiting":[139],"out-of-the-box":[141],"effectiveness":[142],"LLMs":[144],"query":[147,166],"generators.":[148],"address":[150],"these":[151],"by":[153,220,246,262],"developing":[154],"RAG-based":[156],"iterative":[157],"query-generation":[158],"approach":[159],"novel":[162],"self-test":[163],"technique.":[164],"Our":[165],"debugging":[167],"technique":[168],"builds":[169],"on":[170],"idea":[172],"assistive":[174],"queries,":[175],"which":[176],"generate":[177],"concrete":[178],"witnesses":[179],"expose":[181],"explain":[183],"flaws":[185],"candidate":[187],"queries.":[188],"evaluate":[190],"through":[192],"both":[193],"experimental":[194],"user":[196,235],"studies.":[197],"Over":[198],"set":[200],"natural":[202],"derived":[205],"from":[206],"common":[207],"bug-finding":[208],"discovered":[211],"not":[212],"only":[213],"majority":[215],"issues":[218,225],"reported":[219],"other":[221],"approaches,":[222],"but":[223],"also":[224],"would":[227],"have":[228],"otherwise":[229],"remained":[230],"undetected.":[231],"Through":[232],"within-subject":[234],"study,":[236],"found":[238],"access":[240],"increased":[243],"task":[244],"accuracy":[245],"average":[248],"3.8*":[250],"simultaneously":[252],"reduced":[253],"time":[255],"programmers":[257],"complete":[259],"all":[260],"tasks":[261],"31%.":[263]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-05-13T00:00:00"}