{"id":"https://openalex.org/W7204975254","doi":null,"title":"Large language models (LLMs) for legal analysis: RAG and beyond for optimizing domain adaptation in Portuguese legal domain","display_name":"Large language models (LLMs) for legal analysis: RAG and beyond for optimizing domain adaptation in Portuguese legal domain","publication_year":2024,"publication_date":"2024-12-17","ids":{"openalex":"https://openalex.org/W7204975254"},"language":"en","primary_location":{"id":"pmh:oai:run.unl.pt:10362/203859","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10362/203859","pdf_url":"https://run.unl.pt/bitstreams/5e0a1d56-9b17-41c2-9f27-e5c6e12bd4f1/download","source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"master thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://run.unl.pt/bitstreams/5e0a1d56-9b17-41c2-9f27-e5c6e12bd4f1/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148880950","display_name":"Tiago Mendon\u00e7a Alencar Barros","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Barros, Tiago Mendon\u00e7a Alencar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5148880950"],"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/T13643","display_name":"Artificial Intelligence in Law","score":0.5170999765396118,"subfield":{"id":"https://openalex.org/subfields/3308","display_name":"Law"},"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":0.5170999765396118,"subfield":{"id":"https://openalex.org/subfields/3308","display_name":"Law"},"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":0.4652999937534332,"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":0.005400000140070915,"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/large-language-models","display_name":"large language models","score":0.9570000171661377},{"id":"https://openalex.org/keywords/legal-question-answering","display_name":"legal question answering","score":0.6620000004768372},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9610000252723694},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"domain adaptation","score":0.9039999842643738},{"id":"https://openalex.org/keywords/chunking-strategies","display_name":"chunking strategies","score":0.7369999885559082},{"id":"https://openalex.org/keywords/chunk-size","display_name":"chunk size","score":0.7459999918937683},{"id":"https://openalex.org/keywords/self-reflection","display_name":"self-reflection","score":0.9470000267028809},{"id":"https://openalex.org/keywords/linguistic-bias","display_name":"language bias","score":0.7260000109672546},{"id":"https://openalex.org/keywords/underrepresented-languages","display_name":"underrepresented languages","score":0.8519999980926514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7465999722480774},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5831000208854675},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.58160001039505},{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.5669999718666077},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5480999946594238},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5285999774932861},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5180000066757202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5170999765396118},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4325000047683716},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.39739999175071716},{"id":"https://openalex.org/C2778880076","wikidata":"https://www.wikidata.org/wiki/Q750553","display_name":"Brazilian Portuguese","level":3,"score":0.33469998836517334},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.314300000667572},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25440001487731934},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:run.unl.pt:10362/203859","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10362/203859","pdf_url":"https://run.unl.pt/bitstreams/5e0a1d56-9b17-41c2-9f27-e5c6e12bd4f1/download","source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"master thesis"}],"best_oa_location":{"id":"pmh:oai:run.unl.pt:10362/203859","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10362/203859","pdf_url":"https://run.unl.pt/bitstreams/5e0a1d56-9b17-41c2-9f27-e5c6e12bd4f1/download","source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"master thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204975254.pdf","grobid_xml":"https://content.openalex.org/works/W7204975254.grobid-xml"},"referenced_works_count":66,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2594475271","https://openalex.org/W2626778328","https://openalex.org/W2804897457","https://openalex.org/W2963866616","https://openalex.org/W2983040767","https://openalex.org/W3001279689","https://openalex.org/W3025095288","https://openalex.org/W3027879771","https://openalex.org/W3030163527","https://openalex.org/W3092129462","https://openalex.org/W3109650690","https://openalex.org/W3124341041","https://openalex.org/W3124443940","https://openalex.org/W3174681481","https://openalex.org/W3179862281","https://openalex.org/W3185180031","https://openalex.org/W3195577433","https://openalex.org/W3204112174","https://openalex.org/W4293112739","https://openalex.org/W4313491934","https://openalex.org/W4322718191","https://openalex.org/W4353015365","https://openalex.org/W4362515116","https://openalex.org/W4378465439","https://openalex.org/W4382618722","https://openalex.org/W4384918448","https://openalex.org/W4385220584","https://openalex.org/W4385570658","https://openalex.org/W4386724197","https://openalex.org/W4388994251","https://openalex.org/W4389518671","https://openalex.org/W4389984066","https://openalex.org/W4391709255","https://openalex.org/W4392929731","https://openalex.org/W4394946805","https://openalex.org/W4395686609","https://openalex.org/W4396227507","https://openalex.org/W4399198436","https://openalex.org/W4399510390","https://openalex.org/W4399528455","https://openalex.org/W4400064731","https://openalex.org/W4400389996","https://openalex.org/W4401042336","https://openalex.org/W4401306278","https://openalex.org/W4401337436","https://openalex.org/W4401857375","https://openalex.org/W4403006857","https://openalex.org/W4403401276","https://openalex.org/W4403499178","https://openalex.org/W4403570574","https://openalex.org/W4403651347","https://openalex.org/W4403746919","https://openalex.org/W4404782705","https://openalex.org/W4404782883","https://openalex.org/W4404782930","https://openalex.org/W4406771321","https://openalex.org/W4409362346","https://openalex.org/W4409716856","https://openalex.org/W4411113004","https://openalex.org/W4411113537","https://openalex.org/W4411120544","https://openalex.org/W4411403346","https://openalex.org/W4411549467","https://openalex.org/W4416379250","https://openalex.org/W7133244025"],"related_works":["https://openalex.org/W7204983724","https://openalex.org/W7009984178","https://openalex.org/W7078547505","https://openalex.org/W6982074160","https://openalex.org/W7167443761","https://openalex.org/W4405043058","https://openalex.org/W7108325557","https://openalex.org/W7125712586","https://openalex.org/W7147690272","https://openalex.org/W7135312584"],"abstract_inverted_index":{"This":[0],"study":[1],"explores":[2],"RAG":[3],"systems":[4],"tailored":[5],"to":[6,25,75],"the":[7,51],"Portuguese":[8],"legal":[9],"domain,":[10],"highlighting":[11],"challenges":[12],"in":[13],"underrepresented":[14],"languages.":[15],"Fixed-size":[16],"chunking":[17],"strategies,":[18],"particularly":[19,63],"Token":[20],"Text":[21],"Splitter,":[22],"were":[23],"found":[24],"be":[26,76],"most":[27],"effective,":[28],"while":[29],"more":[30],"advanced":[31],"techniques":[32,59],"like":[33],"Recursive":[34],"and":[35,47],"Semantic":[36],"splitting":[37],"showed":[38],"little":[39],"benefits.":[40],"Larger":[41],"chunk":[42,54],"sizes":[43],"improved":[44],"retrieval":[45],"accuracy":[46],"answer":[48],"quality,":[49],"though":[50],"impact":[52],"of":[53],"overlap":[55],"remains":[56],"inconclusive.":[57],"Self-reflection":[58],"show":[60],"promising":[61],"results,":[62],"for":[64,80],"weaker":[65],"LLMs.":[66],"Techniques":[67],"such":[68],"as":[69],"adding":[70],"a":[71],"pre-post":[72],"translation":[73],"proved":[74],"an":[77],"efficient":[78],"technique":[79],"mitigating":[81],"language":[82],"bias.":[83]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-02T00:00:00"}