{"id":"https://openalex.org/W7204456904","doi":"https://doi.org/10.48550/arxiv.2608.24936","title":"GreenLeaf Law Embed Tiny: A Compact Embedding Model for Legal Domain Retrieval","display_name":"GreenLeaf Law Embed Tiny: A Compact Embedding Model for Legal Domain Retrieval","publication_year":2026,"publication_date":"2026-08-23","ids":{"openalex":"https://openalex.org/W7204456904","doi":"https://doi.org/10.48550/arxiv.2608.24936"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.24936","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24936","pdf_url":"https://arxiv.org/pdf/2608.24936","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2608.24936","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147445121","display_name":"Surya Saka","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Saka, Surya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5147445121"],"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":0.6758000254631042,"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":0.6758000254631042,"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":0.22470000386238098,"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/T13643","display_name":"Artificial Intelligence in Law","score":0.0632999986410141,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding-models","display_name":"embedding models","score":0.5920000076293945},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":0.9039999842643738},{"id":"https://openalex.org/keywords/teacher-student-models","display_name":"teacher-student models","score":0.6610000133514404},{"id":"https://openalex.org/keywords/hard-negative-mining","display_name":"hard negative mining","score":0.8140000104904175},{"id":"https://openalex.org/keywords/domain-specific-fine-tuning","display_name":"domain-specific fine-tuning","score":0.9110000133514404},{"id":"https://openalex.org/keywords/quantization","display_name":"quantization","score":0.6729999780654907},{"id":"https://openalex.org/keywords/inference-efficiency","display_name":"inference efficiency","score":0.6439999938011169},{"id":"https://openalex.org/keywords/resource-constrained-deployment","display_name":"resource-constrained deployment","score":0.734000027179718},{"id":"https://openalex.org/keywords/legal-question-answering","display_name":"legal question answering","score":0.33899998664855957}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7554000020027161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6676999926567078},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6201000213623047},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6195999979972839},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.52920001745224},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4977000057697296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4765999913215637},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4458000063896179},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.40689998865127563},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38519999384880066},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3610999882221222},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33559998869895935},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2741999924182892},{"id":"https://openalex.org/C157170001","wikidata":"https://www.wikidata.org/wiki/Q4781507","display_name":"Applications of artificial intelligence","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2705000042915344},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.2655999958515167},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.26499998569488525},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.2637999951839447},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2635999917984009}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.24936","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24936","pdf_url":"https://arxiv.org/pdf/2608.24936","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.24936","doi":"https://doi.org/10.48550/arxiv.2608.24936","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.24936","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.24936","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24936","pdf_url":"https://arxiv.org/pdf/2608.24936","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204456904.pdf","grobid_xml":"https://content.openalex.org/works/W7204456904.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7130608681","https://openalex.org/W7160416237","https://openalex.org/W7164572015","https://openalex.org/W3174504910","https://openalex.org/W4416246791","https://openalex.org/W4416023537","https://openalex.org/W7147695708","https://openalex.org/W4412447705","https://openalex.org/W7128633160","https://openalex.org/W7108325557"],"abstract_inverted_index":{"We":[0,100],"present":[1],"GreenLeaf":[2],"Law":[3],"Embed":[4],"Tiny,":[5],"a":[6,40,49,54,66],"0.6B":[7],"parameter":[8],"embedding":[9],"model":[10,52],"for":[11,129],"legal":[12,81,114],"domain":[13,131],"retrieval.":[14],"GreenLeaf-Tiny":[15],"achieves":[16],"75.11%":[17],"on":[18,27],"the":[19],"Massive":[20],"Legal":[21],"Embedding":[22],"Benchmark":[23],"(MLEB)":[24],"and":[25,83,110],"64.38%":[26],"MTEB(Law,":[28],"v1),demonstrating":[29],"competitive":[30],"performance":[31,128],"among":[32],"models":[33],"under":[34],"1B":[35],"parameters.":[36],"Our":[37,117],"approach":[38],"combines":[39],"two-stage":[41],"training":[42,106,122],"pipeline":[43],"that":[44,120],"first":[45],"distills":[46],"knowledge":[47],"from":[48],"larger":[50],"teacher":[51],"into":[53],"compact":[55],"student":[56],"architecture,":[57],"then":[58],"applies":[59],"domain-specific":[60,121],"fine-tuning":[61],"with":[62,123],"hard":[63],"negative":[64],"mining;":[65],"carefully":[67],"curated":[68],"dataset":[69],"of":[70,104],"3.4":[71],"million":[72],"query-passage":[73],"pairs,":[74],"including":[75],"150,000":[76],"human-curated":[77],"samples":[78],"across":[79,113],"diverse":[80],"jurisdictions;":[82],"an":[84],"efficient":[85],"inference":[86],"architecture":[87],"supporting":[88],"multiple":[89],"quantization":[90],"levels":[91],"(BF16,":[92],"INT8,":[93],"binary)":[94],"enabling":[95],"deployment":[96],"in":[97],"resource-constrained":[98],"environments.":[99],"provide":[101],"detailed":[102],"analysis":[103],"our":[105],"methodology,":[107],"architectural":[108],"choices,":[109],"comprehensive":[111],"evaluation":[112],"retrieval":[115],"tasks.":[116],"results":[118],"demonstrate":[119],"high-quality":[124],"data":[125],"can":[126],"improve":[127],"specialized":[130],"applications":[132]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-28T00:00:00"}