{"id":"https://openalex.org/W4416154653","doi":"https://doi.org/10.48550/arxiv.2502.20364","title":"Bridging Legal Knowledge and AI: Retrieval-Augmented Generation with Vector Stores, Knowledge Graphs, and Hierarchical Non-negative Matrix Factorization","display_name":"Bridging Legal Knowledge and AI: Retrieval-Augmented Generation with Vector Stores, Knowledge Graphs, and Hierarchical Non-negative Matrix Factorization","publication_year":2025,"publication_date":"2025-02-27","ids":{"openalex":"https://openalex.org/W4416154653","doi":"https://doi.org/10.48550/arxiv.2502.20364"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2502.20364","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.20364","pdf_url":"https://arxiv.org/pdf/2502.20364","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/2502.20364","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082439654","display_name":"Ryan Barron","orcid":"https://orcid.org/0009-0005-5045-9527","observed_orcids":["https://orcid.org/0009-0005-5045-9527"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Barron, Ryan C.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066261993","display_name":"Maksim E. Eren","orcid":"https://orcid.org/0000-0002-4362-0256","observed_orcids":["https://orcid.org/0000-0002-4362-0256"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eren, Maksim E.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120595276","display_name":"Olga M. Serafimova","orcid":"https://orcid.org/0009-0006-1185-4636","observed_orcids":["https://orcid.org/0009-0006-1185-4636"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Serafimova, Olga M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019767181","display_name":"Cynthia Matuszek","orcid":"https://orcid.org/0000-0003-1383-8120","observed_orcids":["https://orcid.org/0000-0003-1383-8120"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matuszek, Cynthia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079029372","display_name":"Boian S. Alexandrov","orcid":"https://orcid.org/0000-0001-8636-4603","observed_orcids":["https://orcid.org/0000-0001-8636-4603"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandrov, Boian S.","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":1,"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/T13643","display_name":"Artificial Intelligence in Law","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.0052999998442828655,"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":0.00019999999494757503,"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/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.984000027179718},{"id":"https://openalex.org/keywords/legal-information-retrieval","display_name":"legal information retrieval","score":0.7950000166893005},{"id":"https://openalex.org/keywords/knowledge-graphs","display_name":"knowledge graphs","score":0.8050000071525574},{"id":"https://openalex.org/keywords/vector-store","display_name":"vector store","score":0.9950000047683716},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"non-negative matrix factorization","score":0.8870000243186951},{"id":"https://openalex.org/keywords/legal-research","display_name":"legal research","score":0.6269999742507935},{"id":"https://openalex.org/keywords/legal-document-summarization","display_name":"legal text summarization","score":0.6549999713897705},{"id":"https://openalex.org/keywords/case-law","display_name":"case law","score":0.3540000021457672},{"id":"https://openalex.org/keywords/statutes-and-regulations","display_name":"statutes and regulations","score":0.7129999995231628},{"id":"https://openalex.org/keywords/hallucination-mitigation","display_name":"hallucination mitigation","score":0.7020000219345093},{"id":"https://openalex.org/keywords/topic-detection","display_name":"topic extraction","score":0.4560000002384186},{"id":"https://openalex.org/keywords/computational-law","display_name":"computational law","score":0.5429999828338623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7178000211715698},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.684499979019165},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4853000044822693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43709999322891235},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.4343999922275543},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.423799991607666},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.37720000743865967},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.3619999885559082},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C70587473","wikidata":"https://www.wikidata.org/wiki/Q7834111","display_name":"Transformative learning","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.29440000653266907},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C2993995455","wikidata":"https://www.wikidata.org/wiki/Q3150005","display_name":"Legal document","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C522695570","wikidata":"https://www.wikidata.org/wiki/Q6517578","display_name":"Legal research","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.2565000057220459},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2502.20364","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.20364","pdf_url":"https://arxiv.org/pdf/2502.20364","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.2502.20364","doi":"https://doi.org/10.48550/arxiv.2502.20364","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.20364","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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.20364","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.20364","pdf_url":"https://arxiv.org/pdf/2502.20364","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":[{"score":0.8999999761581421,"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7222974160","https://openalex.org/W7216872307","https://openalex.org/W4405402825","https://openalex.org/W4416615208","https://openalex.org/W4414464073","https://openalex.org/W7155625779","https://openalex.org/W7222616942","https://openalex.org/W4409800684","https://openalex.org/W4416962341","https://openalex.org/W7084104903"],"abstract_inverted_index":{"Agentic":[0],"Generative":[1],"AI,":[2],"powered":[3],"by":[4,62,204],"Large":[5],"Language":[6],"Models":[7],"(LLMs)":[8],"with":[9,69],"Retrieval-Augmented":[10],"Generation":[11],"(RAG),":[12],"Knowledge":[13],"Graphs":[14],"(KGs),":[15],"and":[16,36,65,77,82,90,110,123,126,140,147,153,164,184,201,211,222,227,237],"Vector":[17],"Stores":[18],"(VSs),":[19],"represents":[20],"a":[21,102],"transformative":[22],"technology":[23,43],"applicable":[24],"to":[25,118,138,174],"specialized":[26],"domains":[27],"such":[28,179],"as":[29,180],"legal":[30,55,88,97,120,131,148,155,177,218],"systems,":[31,34],"research,":[32],"recommender":[33],"cybersecurity,":[35],"global":[37],"security,":[38],"including":[39],"proliferation":[40],"research.":[41,98],"This":[42,215],"excels":[44],"at":[45],"inferring":[46],"relationships":[47,152],"within":[48],"vast":[49],"unstructured":[50],"or":[51],"semi-structured":[52,66,231],"datasets.":[53],"The":[54],"domain":[56],"here":[57],"comprises":[58,73],"complex":[59,70,142],"data":[60,232],"characterized":[61],"extensive,":[63],"interrelated,":[64],"knowledge":[67],"systems":[68],"relations.":[71],"It":[72,193],"constitutions,":[74],"statutes,":[75,146,181],"regulations,":[76],"case":[78,185],"law.":[79],"Extracting":[80],"insights":[81],"navigating":[83],"the":[84,130,195],"intricate":[85],"networks":[86],"of":[87],"documents":[89],"their":[91],"relations":[92],"is":[93],"crucial":[94],"for":[95,161,224,230],"effective":[96],"Here,":[99],"we":[100],"introduce":[101],"generative":[103],"AI":[104,124,136],"system":[105,169],"that":[106,158],"integrates":[107],"RAG,":[108],"VS,":[109],"KG,":[111],"constructed":[112],"via":[113],"Non-Negative":[114],"Matrix":[115],"Factorization":[116],"(NMF),":[117],"enhance":[119],"information":[121],"retrieval":[122,229],"reasoning":[125],"minimize":[127],"hallucinations.":[128],"In":[129],"system,":[132],"these":[133],"technologies":[134],"empower":[135],"agents":[137],"identify":[139],"analyze":[141],"connections":[143],"among":[144],"cases,":[145],"precedents,":[149],"uncovering":[150],"hidden":[151],"predicting":[154],"trends-challenging":[156],"tasks":[157],"are":[159],"essential":[160],"ensuring":[162],"justice":[163],"improving":[165],"operational":[166],"efficiency.":[167],"Our":[168],"employs":[170],"web":[171],"scraping":[172],"techniques":[173],"systematically":[175],"collect":[176],"texts,":[178],"constitutional":[182],"provisions,":[183],"law,":[186],"from":[187],"publicly":[188],"accessible":[189],"platforms":[190],"like":[191],"Justia.":[192],"bridges":[194],"gap":[196],"between":[197],"traditional":[198],"keyword-based":[199],"searches":[200],"contextual":[202],"understanding":[203],"leveraging":[205],"advanced":[206],"semantic":[207],"representations,":[208],"hierarchical":[209],"relationships,":[210],"latent":[212],"topic":[213],"discovery.":[214],"framework":[216],"supports":[217],"document":[219],"clustering,":[220],"summarization,":[221],"cross-referencing,":[223],"scalable,":[225],"interpretable,":[226],"accurate":[228],"while":[233],"advancing":[234],"computational":[235],"law":[236],"AI.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-09-21T07:43:02.447757","created_date":"2025-10-10T00:00:00"}