{"id":"https://openalex.org/W4416260006","doi":"https://doi.org/10.5220/0013647300003967","title":"Evaluation of LLM-Based Strategies for the Extraction of Food Product Information from Online Shops","display_name":"Evaluation of LLM-Based Strategies for the Extraction of Food Product Information from Online Shops","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416260006","doi":"https://doi.org/10.5220/0013647300003967"},"language":"en","primary_location":{"id":"doi:10.5220/0013647300003967","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0013647300003967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Conference on Data Science, Technology and Applications","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.21585","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092465684","display_name":"Christoph Brosch","orcid":null},"institutions":[{"id":"https://openalex.org/I137932638","display_name":"Trier University of Applied Sciences","ror":"https://ror.org/02e3hdx05","country_code":"DE","type":"education","lineage":["https://openalex.org/I137932638"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Christoph Brosch","raw_affiliation_strings":["Institute for Software Systems, University of Applied Sciences Trier, Birkenfeld, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Software Systems, University of Applied Sciences Trier, Birkenfeld, Germany","institution_ids":["https://openalex.org/I137932638"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120403800","display_name":"Sian Brumm","orcid":null},"institutions":[{"id":"https://openalex.org/I137932638","display_name":"Trier University of Applied Sciences","ror":"https://ror.org/02e3hdx05","country_code":"DE","type":"education","lineage":["https://openalex.org/I137932638"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sian Brumm","raw_affiliation_strings":["Institute for Software Systems, University of Applied Sciences Trier, Birkenfeld, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Software Systems, University of Applied Sciences Trier, Birkenfeld, Germany","institution_ids":["https://openalex.org/I137932638"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105422327","display_name":"Rolf Krieger","orcid":null},"institutions":[{"id":"https://openalex.org/I137932638","display_name":"Trier University of Applied Sciences","ror":"https://ror.org/02e3hdx05","country_code":"DE","type":"education","lineage":["https://openalex.org/I137932638"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rolf Krieger","raw_affiliation_strings":["Institute for Software Systems, University of Applied Sciences Trier, Birkenfeld, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Software Systems, University of Applied Sciences Trier, Birkenfeld, Germany","institution_ids":["https://openalex.org/I137932638"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006046781","display_name":"J. M. Scheffler","orcid":"https://orcid.org/0000-0001-6360-8820"},"institutions":[{"id":"https://openalex.org/I137932638","display_name":"Trier University of Applied Sciences","ror":"https://ror.org/02e3hdx05","country_code":"DE","type":"education","lineage":["https://openalex.org/I137932638"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jonas Scheffler","raw_affiliation_strings":["Institute for Software Systems, University of Applied Sciences Trier, Birkenfeld, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Software Systems, University of Applied Sciences Trier, Birkenfeld, Germany","institution_ids":["https://openalex.org/I137932638"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5092465684"],"corresponding_institution_ids":["https://openalex.org/I137932638"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.49548569,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"709","last_page":"715"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.6407999992370605,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.6407999992370605,"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":0.026399999856948853,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.026000000536441803,"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/product","display_name":"Product (mathematics)","score":0.5633000135421753},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.487199991941452},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.47040000557899475},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.43709999322891235},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.42809998989105225},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.42800000309944153},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42590001225471497},{"id":"https://openalex.org/keywords/ingredient","display_name":"Ingredient","score":0.390500009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6499999761581421},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.5633000135421753},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.487199991941452},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.47040000557899475},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.43709999322891235},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.42809998989105225},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.42800000309944153},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42590001225471497},{"id":"https://openalex.org/C2780589914","wikidata":"https://www.wikidata.org/wiki/Q10675206","display_name":"Ingredient","level":2,"score":0.390500009059906},{"id":"https://openalex.org/C513059894","wikidata":"https://www.wikidata.org/wiki/Q540912","display_name":"Food industry","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3499000072479248},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3416000008583069},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3246999979019165},{"id":"https://openalex.org/C2987718291","wikidata":"https://www.wikidata.org/wiki/Q2095","display_name":"Food products","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.2953999936580658},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.275299996137619},{"id":"https://openalex.org/C101293273","wikidata":"https://www.wikidata.org/wiki/Q579716","display_name":"User-generated content","level":3,"score":0.273499995470047},{"id":"https://openalex.org/C147101817","wikidata":"https://www.wikidata.org/wiki/Q13443840","display_name":"Product category","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.2590999901294708}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0013647300003967","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0013647300003967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Conference on Data Science, Technology and Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.21585","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.21585","pdf_url":"https://arxiv.org/pdf/2506.21585","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.21585","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.21585","pdf_url":"https://arxiv.org/pdf/2506.21585","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generative":[0],"AI":[1],"and":[2,32,46,56,69,118,132],"large":[3],"language":[4],"models":[5],"(LLMs)":[6],"offer":[7],"significant":[8],"potential":[9],"for":[10,135],"automating":[11],"the":[12,90,105],"extraction":[13,35,55,58,127,138],"of":[14,66,75,107],"structured":[15],"information":[16,137],"from":[17,29,80,140],"web":[18,142],"pages.":[19],"In":[20],"this":[21],"work,":[22],"we":[23],"focus":[24],"on":[25,71],"food":[26,77],"product":[27,40,78],"pages":[28,79,143],"online":[30,83],"retailers":[31],"explore":[33],"schema-constrained":[34],"approaches":[36,128],"to":[37,100,114],"retrieve":[38],"key":[39],"attributes,":[41],"such":[42],"as":[43],"ingredient":[44],"lists":[45],"nutrition":[47],"tables.":[48],"We":[49],"compare":[50],"two":[51],"LLM-based":[52],"approaches,":[53],"direct":[54,101],"indirect":[57,91,126],"via":[59],"generated":[60],"functions,":[61],"evaluating":[62],"them":[63],"in":[64],"terms":[65],"accuracy,":[67],"efficiency,":[68],"cost":[70],"a":[72],"curated":[73],"dataset":[74],"3,000":[76],"three":[81],"different":[82],"shops.":[84],"Our":[85],"results":[86],"show":[87],"that":[88,125],"although":[89],"approach":[92],"achieves":[93],"slightly":[94],"lower":[95,119],"accuracy":[96],"(96.48\\%,":[97],"$-1.61\\%$":[98],"compared":[99],"extraction),":[102],"it":[103],"reduces":[104],"number":[106],"required":[108],"LLM":[109],"calls":[110],"by":[111],"95.82\\%,":[112],"leading":[113],"substantial":[115],"efficiency":[116],"gains":[117],"operational":[120],"costs.":[121],"These":[122],"findings":[123],"suggest":[124],"can":[129],"provide":[130],"scalable":[131],"cost-effective":[133],"solutions":[134],"large-scale":[136],"tasks":[139],"template-based":[141],"using":[144],"LLMs.":[145]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}