{"id":"https://openalex.org/W4416617103","doi":"https://doi.org/10.48550/arxiv.2510.19864","title":"SODBench: A Large Language Model Approach to Documenting Spreadsheet Operations","display_name":"SODBench: A Large Language Model Approach to Documenting Spreadsheet Operations","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416617103","doi":"https://doi.org/10.48550/arxiv.2510.19864"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2510.19864","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.19864","pdf_url":"https://arxiv.org/pdf/2510.19864","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":null,"license_id":null,"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/2510.19864","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030852698","display_name":"Amila Indika","orcid":"https://orcid.org/0000-0003-3379-7047","observed_orcids":["https://orcid.org/0000-0003-3379-7047"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Indika, Amila","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5041560478","display_name":"Igor Molybog","orcid":"https://orcid.org/0000-0001-7251-3532","observed_orcids":["https://orcid.org/0000-0001-7251-3532"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Molybog, Igor","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/T13197","display_name":"Spreadsheets and End-User Computing","score":0.6044999957084656,"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"}},"topics":[{"id":"https://openalex.org/T13197","display_name":"Spreadsheets and End-User Computing","score":0.6044999957084656,"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/T10260","display_name":"Software Engineering Research","score":0.2809999883174896,"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/T10028","display_name":"Topic Modeling","score":0.07429999858140945,"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/natural-language-explanation-generation","display_name":"natural language explanation generation","score":0.7009999752044678},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8859999775886536},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.7379999756813049},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"knowledge transfer","score":0.3869999945163727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8126999735832214},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.7631000280380249},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6815999746322632},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5782999992370605},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5404999852180481},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.5042999982833862},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.501800000667572},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4796000123023987},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.46389999985694885},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3450999855995178},{"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/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3343000113964081},{"id":"https://openalex.org/C67463725","wikidata":"https://www.wikidata.org/wiki/Q17081452","display_name":"Natural language programming","level":5,"score":0.3043999969959259},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.28209999203681946},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2816999852657318},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.26350000500679016},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C81587897","wikidata":"https://www.wikidata.org/wiki/Q181702","display_name":"Software documentation","level":5,"score":0.25699999928474426}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2510.19864","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.19864","pdf_url":"https://arxiv.org/pdf/2510.19864","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.19864","doi":"https://doi.org/10.48550/arxiv.2510.19864","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.19864","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.19864","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.19864","pdf_url":"https://arxiv.org/pdf/2510.19864","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Numerous":[0],"knowledge":[1,23],"workers":[2],"utilize":[3],"spreadsheets":[4,18],"in":[5,139],"business,":[6],"accounting,":[7],"and":[8,22,107,113,136],"finance.":[9],"However,":[10],"a":[11,75,83,94,128],"lack":[12],"of":[13,29,85],"systematic":[14],"documentation":[15],"methods":[16],"for":[17,60,72],"hinders":[19],"automation,":[20],"collaboration,":[21],"transfer,":[24],"which":[25],"risks":[26],"the":[27],"loss":[28],"crucial":[30],"institutional":[31],"knowledge.":[32],"This":[33],"paper":[34],"introduces":[35],"Spreadsheet":[36],"Operations":[37],"Documentation":[38],"(SOD),":[39],"an":[40],"AI":[41],"task":[42],"that":[43,67,119,145],"involves":[44],"generating":[45,61],"human-readable":[46],"explanations":[47],"from":[48],"spreadsheet":[49,62,87,124],"operations.":[50],"Many":[51],"previous":[52],"studies":[53],"have":[54],"utilized":[55],"Large":[56],"Language":[57],"Models":[58],"(LLMs)":[59],"manipulation":[63,88],"code;":[64],"however,":[65],"translating":[66],"code":[68,89],"into":[69],"natural":[70,96],"language":[71,97],"SOD":[73,127],"is":[74],"less-explored":[76],"area.":[77],"To":[78],"address":[79],"this,":[80],"we":[81],"present":[82],"benchmark":[84],"111":[86],"snippets,":[90],"each":[91],"paired":[92],"with":[93],"corresponding":[95],"summary.":[98],"We":[99],"evaluate":[100],"five":[101],"LLMs,":[102],"GPT-4o,":[103],"GPT-4o-mini,":[104],"LLaMA-3.3-70B,":[105],"Mixtral-8x7B,":[106],"Gemma2-9B,":[108],"using":[109],"BLEU,":[110],"GLEU,":[111],"ROUGE-L,":[112],"METEOR":[114],"metrics.":[115],"Our":[116],"findings":[117],"suggest":[118],"LLMs":[120],"can":[121],"generate":[122],"accurate":[123],"documentation,":[125],"making":[126],"feasible":[129],"prerequisite":[130],"step":[131],"toward":[132],"enhancing":[133],"reproducibility,":[134],"maintainability,":[135],"collaborative":[137],"workflows":[138],"spreadsheets,":[140],"although":[141],"there":[142],"are":[143],"challenges":[144],"need":[146],"to":[147],"be":[148],"addressed.":[149]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-25T00:00:00"}