{"id":"https://openalex.org/W7167891232","doi":"https://doi.org/10.1145/3805712.3808529","title":"Bridging the Language Gap in Text-to-SQL: Adapting LLMs for Chichewa in a Low-Resource Setting","display_name":"Bridging the Language Gap in Text-to-SQL: Adapting LLMs for Chichewa in a Low-Resource Setting","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167891232","doi":"https://doi.org/10.1145/3805712.3808529"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3808529","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808529","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3808529","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134377368","display_name":"John Emeka Eze","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112059","display_name":"African Institute for Mathematical Sciences","ror":"https://ror.org/02w32z542","country_code":"RW","type":"education","lineage":["https://openalex.org/I4210112059"]}],"countries":["RW"],"is_corresponding":false,"raw_author_name":"John Emeka Eze","raw_affiliation_strings":["African Institute for Mathematical Sciences, Kigali, Rwanda"],"raw_orcid":"https://orcid.org/0009-0008-0688-5125","affiliations":[{"raw_affiliation_string":"African Institute for Mathematical Sciences, Kigali, Rwanda","institution_ids":["https://openalex.org/I4210112059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085537594","display_name":"Dunstan Matekenya","orcid":null},"institutions":[{"id":"https://openalex.org/I55633929","display_name":"World Bank Group","ror":"https://ror.org/02md09461","country_code":"US","type":"other","lineage":["https://openalex.org/I55633929"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dunstan Matekenya","raw_affiliation_strings":["The World Bank Group, Washington DC, USA"],"raw_orcid":"https://orcid.org/0009-0002-4484-8890","affiliations":[{"raw_affiliation_string":"The World Bank Group, Washington DC, USA","institution_ids":["https://openalex.org/I55633929"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140398177","display_name":"Evance Mathewe","orcid":"https://orcid.org/0009-0006-4170-6749"},"institutions":[{"id":"https://openalex.org/I55633929","display_name":"World Bank Group","ror":"https://ror.org/02md09461","country_code":"US","type":"other","lineage":["https://openalex.org/I55633929"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evance Mathewe","raw_affiliation_strings":["The World Bank Group, Washington DC, USA"],"raw_orcid":"https://orcid.org/0009-0006-4170-6749","affiliations":[{"raw_affiliation_string":"The World Bank Group, Washington DC, USA","institution_ids":["https://openalex.org/I55633929"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93913503,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5266","last_page":"5269"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13194","display_name":"ICT in Developing Communities","score":0.28299999237060547,"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/T13194","display_name":"ICT in Developing Communities","score":0.28299999237060547,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.06109999865293503,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.04230000078678131,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.7049999833106995},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5909000039100647},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5490000247955322},{"id":"https://openalex.org/keywords/bantu-languages","display_name":"Bantu languages","score":0.5473999977111816},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4025999903678894},{"id":"https://openalex.org/keywords/first-language","display_name":"First language","score":0.37770000100135803},{"id":"https://openalex.org/keywords/commodity","display_name":"Commodity","score":0.33889999985694885}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.7049999833106995},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5909000039100647},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5490000247955322},{"id":"https://openalex.org/C99878080","wikidata":"https://www.wikidata.org/wiki/Q33146","display_name":"Bantu languages","level":2,"score":0.5473999977111816},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4961000084877014},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C2779439359","wikidata":"https://www.wikidata.org/wiki/Q317088","display_name":"Commodity","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33660000562667847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3334999978542328},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.28780001401901245},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C2780789378","wikidata":"https://www.wikidata.org/wiki/Q23492","display_name":"Official language","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.258899986743927},{"id":"https://openalex.org/C189326681","wikidata":"https://www.wikidata.org/wiki/Q10294","display_name":"Poverty","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C2780566098","wikidata":"https://www.wikidata.org/wiki/Q25295","display_name":"Language family","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3808529","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808529","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3808529","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808529","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2","score":0.5867965221405029}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2890431379","https://openalex.org/W3035032094","https://openalex.org/W3098998028","https://openalex.org/W4412377096","https://openalex.org/W7133233472"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,12,18,37,49,70,100,150,181],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"have":[7],"significantly":[8],"improved":[9],"Text-to-SQL":[10,35,59],"performance":[11],"high-resource":[13],"languages.":[14],"However,":[15],"their":[16],"effectiveness":[17],"low-resource":[19,40],"language":[20,42,159],"settings":[21],"remains":[22],"largely":[23],"underexplored.":[24],"In":[25],"this":[26,158,161],"work,":[27],"we":[28],"investigate":[29],"the":[30,117,153,165],"adaptation":[31],"of":[32,62,120],"LLMs":[33,91],"for":[34,157,177],"generation":[36],"Chichewa,":[38,151],"a":[39,56,71],"Bantu":[41],"spoken":[43],"by":[44],"over":[45],"12":[46],"million":[47],"people":[48],"Malawi":[50],"and":[51,83,96,103,134,163],"neighboring":[52],"regions.":[53],"We":[54,86,105],"construct":[55],"structured":[57],"Chichewa":[58,135],"benchmark":[60,162],"consisting":[61],"400":[63],"manually":[64],"curated":[65],"natural":[66],"language\u2013SQL":[67],"pairs":[68],"grounded":[69],"unified":[72],"relational":[73],"database":[74,179],"covering":[75],"agriculture,":[76],"commodity":[77],"prices,":[78],"population":[79],"statistics,":[80],"market":[81],"data,":[82],"food":[84],"insecurity.":[85],"systematically":[87],"evaluate":[88,116],"five":[89],"open-source":[90],"under":[92],"zero-shot,":[93],"random":[94],"5-shot,":[95],"retrieval-augmented":[97,124,143],"5-shot":[98],"prompting,":[99,144],"both":[101],"English":[102,129],"Chichewa.":[104],"then":[106],"apply":[107],"parameter-efficient":[108],"fine-tuning":[109,122],"(QLoRA)":[110],"to":[111,132,138,168],"selected":[112],"models":[113],"and,":[114],"crucially,":[115],"combined":[118,141],"effect":[119],"QLoRA":[121,126,145],"with":[123,142],"prompting.":[125],"alone":[127],"improves":[128],"execution":[130,136,148],"accuracy":[131,137,149],"78.3%":[133],"41.7%.":[139],"When":[140],"achieves":[146],"53.3%":[147],"representing":[152],"best":[154],"reported":[155],"result":[156],"on":[160],"narrowing":[164],"English\u2013Chichewa":[166],"gap":[167],"23.4":[169],"percentage":[170],"points.":[171],"Our":[172],"findings":[173],"offer":[174],"practical":[175],"guidance":[176],"deploying":[178],"interfaces":[180],"linguistically":[182],"underserved":[183],"environments.":[184]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-11T00:00:00"}
