{"id":"https://openalex.org/W7115289017","doi":null,"title":"Answer validation using Large Language Model Systems","display_name":"Answer validation using Large Language Model Systems","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7115289017"},"language":"en","primary_location":{"id":"pmh:oai:www.doria.fi:10024/192909","doi":null,"is_oa":true,"landing_page_url":"https://www.doria.fi/handle/10024/192909","pdf_url":"https://www.doria.fi/bitstream/10024/192909/3/bitarafan_ali.pdf","source":{"id":"https://openalex.org/S4377196760","display_name":"Doria (University of Helsinki)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I133731052","host_organization_name":"University of Helsinki","host_organization_lineage":["https://openalex.org/I133731052"],"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":"Avhandling pro gradu"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.doria.fi/bitstream/10024/192909/3/bitarafan_ali.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bitarafan, Ali","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bitarafan, Ali","raw_affiliation_strings":[", Turku , Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":", Turku , Finland","institution_ids":[]}]}],"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":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/T10028","display_name":"Topic Modeling","score":0.9467999935150146,"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":0.9467999935150146,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.016300000250339508,"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":0.01590000092983246,"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/answer-validation","display_name":"answer validation","score":0.8519999980926514},{"id":"https://openalex.org/keywords/automated-assessment","display_name":"automated assessment","score":0.574999988079071},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9150000214576721},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9940000176429749},{"id":"https://openalex.org/keywords/free-text-answers","display_name":"free-text answers","score":0.7839999794960022},{"id":"https://openalex.org/keywords/factual-grounding","display_name":"factual grounding","score":0.6380000114440918},{"id":"https://openalex.org/keywords/knowledge-base-retrieval","display_name":"knowledge base retrieval","score":0.7200000286102295},{"id":"https://openalex.org/keywords/document-indexing","display_name":"document indexing","score":0.6359999775886536},{"id":"https://openalex.org/keywords/low-resource-models","display_name":"low-resource models","score":0.5230000019073486},{"id":"https://openalex.org/keywords/ollama","display_name":"Ollama","score":0.6290000081062317},{"id":"https://openalex.org/keywords/langchain","display_name":"LangChain","score":0.8119999766349792},{"id":"https://openalex.org/keywords/processing-delay","display_name":"processing delay","score":0.46399998664855957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.864799976348877},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6624000072479248},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5954999923706055},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5109999775886536},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.49380001425743103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45339998602867126},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4390999972820282},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.424699991941452},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40799999237060547},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.40070000290870667},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.39070001244544983},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3894999921321869},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3652999997138977},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3644999861717224},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34310001134872437},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C2780613888","wikidata":"https://www.wikidata.org/wiki/Q6423394","display_name":"Knowledge retrieval","level":3,"score":0.30239999294281006},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28360000252723694},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2671999931335449},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:www.doria.fi:10024/192909","doi":null,"is_oa":true,"landing_page_url":"https://www.doria.fi/handle/10024/192909","pdf_url":"https://www.doria.fi/bitstream/10024/192909/3/bitarafan_ali.pdf","source":{"id":"https://openalex.org/S4377196760","display_name":"Doria (University of Helsinki)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I133731052","host_organization_name":"University of Helsinki","host_organization_lineage":["https://openalex.org/I133731052"],"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":"Avhandling pro gradu"}],"best_oa_location":{"id":"pmh:oai:www.doria.fi:10024/192909","doi":null,"is_oa":true,"landing_page_url":"https://www.doria.fi/handle/10024/192909","pdf_url":"https://www.doria.fi/bitstream/10024/192909/3/bitarafan_ali.pdf","source":{"id":"https://openalex.org/S4377196760","display_name":"Doria (University of Helsinki)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I133731052","host_organization_name":"University of Helsinki","host_organization_lineage":["https://openalex.org/I133731052"],"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":"Avhandling pro gradu"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7115289017.pdf","grobid_xml":"https://content.openalex.org/works/W7115289017.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2626778328","https://openalex.org/W3027879771","https://openalex.org/W3034085606","https://openalex.org/W3210904070","https://openalex.org/W4401484139","https://openalex.org/W4403212614","https://openalex.org/W4406756422","https://openalex.org/W4416379250"],"related_works":["https://openalex.org/W7133715678","https://openalex.org/W4406457822","https://openalex.org/W7199584589","https://openalex.org/W6931042154","https://openalex.org/W4389984066","https://openalex.org/W7162439475","https://openalex.org/W7217751011","https://openalex.org/W7045621831","https://openalex.org/W7160492840","https://openalex.org/W6964671770"],"abstract_inverted_index":{"Assessing":[0],"candidate":[1],"knowledge":[2,51,77,179,190],"through":[3],"free-text":[4],"answers":[5],"poses":[6],"significant":[7],"challenges":[8],"for":[9,49,188],"automation,":[10],"often":[11],"hindered":[12],"by":[13,43,120],"the":[14,44,88,111,126,142,162,173,178,196],"scalability":[15],"and":[16,90,99,103,133,168,175],"consistency":[17],"limitations":[18],"of":[19,93,113,144,177],"traditional":[20],"methods":[21],"like":[22],"manual":[23],"grading":[24],"or":[25],"simple":[26],"keyword":[27],"matching.":[28],"In":[29],"this":[30,114],"thesis,":[31],"we":[32],"investigate":[33],"an":[34,83,107],"application":[35,108],"workflow":[36],"leveraging":[37],"Large":[38],"Language":[39],"Models":[40],"(LLMs),":[41],"enhanced":[42],"Retrieval-Augmented":[45],"Generation":[46,64],"(RAG)":[47,65],"framework,":[48],"automated":[50,189],"validation":[52],"against":[53],"domain-specific":[54],"documents.":[55],"We":[56,97,149],"present":[57,184],"a":[58,75,94,169,185],"system":[59,128,156],"architecture":[60],"where":[61],"Retrieval":[62],"Augmented":[63],"is":[66],"utilized":[67],"to":[68,79,82,109,137,161],"dynamically":[69],"retrieve":[70],"relevant":[71],"factual":[72,131],"passages":[73],"from":[74],"designated":[76],"corpus":[78],"provide":[80],"context":[81],"LLM,":[84],"which":[85],"then":[86],"evaluates":[87],"correctness":[89],"contextual":[91,134],"relevance":[92],"candidate's":[95],"answer.":[96],"implement":[98],"evaluate":[100],"(via":[101],"LangChain":[102],"Ollama":[104],"open-source":[105],"libraries)":[106],"assess":[110],"practicality":[112],"approach":[115],"given":[116],"hardware":[117],"constraints":[118],"imposed":[119],"commercial":[121],"computers.":[122],"Findings":[123],"indicate":[124],"that":[125],"RAG-enhanced":[127,182],"significantly":[129],"improves":[130],"grounding":[132],"understanding":[135],"compared":[136],"standalone":[138],"LLMs,":[139],"potentially":[140],"allowing":[141],"use":[143],"smaller,":[145],"more":[146],"resource-efficient":[147],"models.":[148],"also":[150],"spot":[151],"critical":[152],"challenges,":[153],"including":[154],"increased":[155],"complexity,":[157],"processing":[158],"latency":[159],"due":[160],"retrieval":[163],"step,":[164],"slow":[165],"document":[166],"indexing,":[167],"crucial":[170],"dependency":[171],"on":[172],"quality":[174],"comprehensiveness":[176],"base.":[180],"While":[181],"LLMs":[183],"promising":[186],"advancement":[187],"evaluation,":[191],"successful":[192],"deployment":[193],"requires":[194],"balancing":[195],"benefits":[197],"with":[198],"these":[199],"practical":[200],"considerations.":[201]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-12-15T00:00:00"}