{"id":"https://openalex.org/W4411418916","doi":"https://doi.org/10.1007/s44443-025-00071-w","title":"Automatic XPath generation agents for vertical websites by LLMs","display_name":"Automatic XPath generation agents for vertical websites by LLMs","publication_year":2025,"publication_date":"2025-06-18","ids":{"openalex":"https://openalex.org/W4411418916","doi":"https://doi.org/10.1007/s44443-025-00071-w"},"language":"en","primary_location":{"id":"doi:10.1007/s44443-025-00071-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-025-00071-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44443-025-00071-w.pdf","source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s44443-025-00071-w.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038183599","display_name":"Jing Huang","orcid":"https://orcid.org/0000-0002-5294-2572"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210096250","display_name":"Beijing Institute of Big Data Research","ror":"https://ror.org/00s1sz824","country_code":"CN","type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I37796252","https://openalex.org/I4210096250"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jing Huang","raw_affiliation_strings":["ChongQing Research Institute of Big Data, Chongqing, 401329, PR China","College of Engineering, Peking University, Beijing, 100871, PR China","National Engineering Laboratory For Big Data Analysis and Applications, Beijing, 100871, PR China"],"affiliations":[{"raw_affiliation_string":"ChongQing Research Institute of Big Data, Chongqing, 401329, PR China","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"College of Engineering, Peking University, Beijing, 100871, PR China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"National Engineering Laboratory For Big Data Analysis and Applications, Beijing, 100871, PR China","institution_ids":["https://openalex.org/I4210096250"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004612882","display_name":"Jie Song","orcid":"https://orcid.org/0000-0003-0704-3217"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210096250","display_name":"Beijing Institute of Big Data Research","ror":"https://ror.org/00s1sz824","country_code":"CN","type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I37796252","https://openalex.org/I4210096250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Song","raw_affiliation_strings":["College of Engineering, Peking University, Beijing, 100871, PR China","National Engineering Laboratory For Big Data Analysis and Applications, Beijing, 100871, PR China"],"affiliations":[{"raw_affiliation_string":"College of Engineering, Peking University, Beijing, 100871, PR China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"National Engineering Laboratory For Big Data Analysis and Applications, Beijing, 100871, PR China","institution_ids":["https://openalex.org/I4210096250"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5038183599"],"corresponding_institution_ids":["https://openalex.org/I158842170","https://openalex.org/I20231570","https://openalex.org/I4210096250"],"apc_list":{"value":1350,"currency":"USD","value_usd":1350},"apc_paid":{"value":1350,"currency":"USD","value_usd":1350},"fwci":3.2508,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91837858,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"37","issue":"5","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9993000030517578,"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":0.9993000030517578,"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/T13999","display_name":"Digital Rights Management and Security","score":0.9908999800682068,"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/T11719","display_name":"Data Quality and Management","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/xpath","display_name":"XPath","score":0.9100759029388428},{"id":"https://openalex.org/keywords/rewriting","display_name":"Rewriting","score":0.48020705580711365},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4256390333175659},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.32327619194984436},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.24551668763160706},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14347141981124878},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.08792480826377869}],"concepts":[{"id":"https://openalex.org/C2780213375","wikidata":"https://www.wikidata.org/wiki/Q16340","display_name":"XPath","level":4,"score":0.9100759029388428},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.48020705580711365},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4256390333175659},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.32327619194984436},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.24551668763160706},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14347141981124878},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.08792480826377869},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44443-025-00071-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-025-00071-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44443-025-00071-w.pdf","source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7f3c9f43fd744e388bfa90967f7dac88","is_oa":true,"landing_page_url":"https://doaj.org/article/7f3c9f43fd744e388bfa90967f7dac88","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of King Saud University: Computer and Information Sciences, Vol 37, Iss 5, Pp 1-17 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44443-025-00071-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-025-00071-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44443-025-00071-w.pdf","source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411418916.pdf","grobid_xml":"https://content.openalex.org/works/W4411418916.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2148317291","https://openalex.org/W2161861392","https://openalex.org/W2584049620","https://openalex.org/W2805173585","https://openalex.org/W2955858358","https://openalex.org/W2963748441","https://openalex.org/W3035131649","https://openalex.org/W3081176230","https://openalex.org/W3099461227","https://openalex.org/W3105188155","https://openalex.org/W3176664887","https://openalex.org/W3206324399","https://openalex.org/W4221167659","https://openalex.org/W4281488715","https://openalex.org/W4315642533","https://openalex.org/W4385565111","https://openalex.org/W4387299960","https://openalex.org/W4389520219","https://openalex.org/W4391292768","https://openalex.org/W4394673924","https://openalex.org/W4396673725","https://openalex.org/W4402670253","https://openalex.org/W4404781305","https://openalex.org/W4404782707","https://openalex.org/W6600109629","https://openalex.org/W6602430550","https://openalex.org/W6602703391","https://openalex.org/W6608332583","https://openalex.org/W6631231910","https://openalex.org/W6756688054"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1542110834","https://openalex.org/W2611888112","https://openalex.org/W2121120069","https://openalex.org/W562932586","https://openalex.org/W2124793519","https://openalex.org/W2398280235","https://openalex.org/W2054675674"],"abstract_inverted_index":{"Extracting":[0],"structured":[1,85,106,161],"data":[2,16,108,162],"from":[3,38,92,141,164,183],"web":[4,100,107],"pages":[5,94],"has":[6,27],"long":[7],"been":[8],"a":[9,69,74,174],"challenging":[10],"research":[11],"topic,":[12],"particularly":[13],"for":[14,31,118,171],"domain-specific":[15],"on":[17,104,180],"vertical":[18,119,165],"websites.":[19],"The":[20,150],"advent":[21],"of":[22,160,176],"large":[23],"language":[24],"models":[25],"(LLMs)":[26],"introduced":[28],"new":[29,70],"possibilities":[30],"this":[32,50,113],"task,":[33],"enabling":[34,78],"high-accuracy":[35],"information":[36,182],"extraction":[37,109,163],"individual":[39],"pages.":[40,101],"However,":[41],"due":[42],"to":[43,58,87,98,143],"the":[44,130,156],"substantial":[45],"costs":[46],"associated":[47],"with":[48,121],"LLMs,":[49,79],"approach":[51,127],"is":[52],"often":[53],"economically":[54],"impractical":[55],"and":[56,95,135,158],"difficult":[57],"scale":[59],"in":[60,83],"industrial":[61,177],"applications.":[62],"To":[63],"address":[64],"these":[65],"challenges":[66],"we":[67],"propose":[68],"framework":[71,114,152],"that":[72,112],"leverages":[73],"multi-task":[75],"decomposition":[76],"strategy,":[77],"despite":[80],"their":[81],"limitations":[82],"handling":[84],"information,":[86],"learn":[88],"robust":[89],"XPath":[90],"expressions":[91],"seed":[93],"apply":[96],"them":[97],"unseen":[99],"Experimental":[102],"results":[103],"various":[105],"datasets":[110],"demonstrate":[111],"achieves":[115],"state-of-the-art":[116],"accuracy":[117,157],"websites":[120],"minimal":[122],"LLM":[123],"interactions.":[124],"Furthermore,":[125],"our":[126],"significantly":[128],"outperforms":[129],"top":[131],"prompting-based":[132],"methods,":[133],"Reflexion":[134],"COT,":[136],"improving":[137],"F1":[138],"scores":[139],"ranging":[140],"14.84":[142],"23.86":[144],"percentage":[145],"points":[146],"across":[147,173],"multiple":[148],"datasets.":[149],"proposed":[151],"not":[153],"only":[154],"boosts":[155],"efficiency":[159],"websites,":[166],"but":[167],"also":[168],"holds":[169],"promise":[170],"adaptation":[172],"range":[175],"applications":[178],"focused":[179],"extracting":[181],"hierarchical":[184],"data.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
