{"id":"https://openalex.org/W4416034858","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.742","title":"Evaluating Test-Time Scaling LLMs for Legal Reasoning: OpenAI o1, DeepSeek-R1, and Beyond","display_name":"Evaluating Test-Time Scaling LLMs for Legal Reasoning: OpenAI o1, DeepSeek-R1, and Beyond","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034858","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.742"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.742","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.742","pdf_url":"https://aclanthology.org/2025.findings-emnlp.742.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.742.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039876879","display_name":"Yinghao Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yinghao Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103326680","display_name":"Y.T. Yu","orcid":"https://orcid.org/0009-0008-3253-7247"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaoyao Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063264979","display_name":"Leilei Gan","orcid":"https://orcid.org/0000-0001-5859-2588"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leilei Gan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101632069","display_name":"Bin Wei","orcid":"https://orcid.org/0000-0003-4635-7550"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bin Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041727387","display_name":"Kun Kuang","orcid":"https://orcid.org/0000-0001-7024-9790"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Kuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5007358266","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0002-0909-7596"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35050297,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13759","last_page":"13781"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.41839998960494995,"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":0.41839998960494995,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.09849999845027924,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.05550000071525574,"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/context","display_name":"Context (archaeology)","score":0.25380000472068787},{"id":"https://openalex.org/keywords/government","display_name":"Government (linguistics)","score":0.2498999983072281},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.24889999628067017}],"concepts":[{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.6279000043869019},{"id":"https://openalex.org/C100001284","wikidata":"https://www.wikidata.org/wiki/Q2248246","display_name":"Public economics","level":1,"score":0.4034000039100647},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.2957000136375427},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.28380000591278076},{"id":"https://openalex.org/C47768531","wikidata":"https://www.wikidata.org/wiki/Q1127188","display_name":"Development economics","level":1,"score":0.2619999945163727},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.25619998574256897},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.2498999983072281},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.24889999628067017},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2476000040769577}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.742","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.742","pdf_url":"https://aclanthology.org/2025.findings-emnlp.742.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.742","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.742","pdf_url":"https://aclanthology.org/2025.findings-emnlp.742.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034858.pdf","grobid_xml":"https://content.openalex.org/works/W4416034858.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,110],"test-time":[3],"scaling":[4],"of":[5,21,33,51],"large":[6],"language":[7],"models":[8],"(LLMs),":[9],"exemplified":[10],"by":[11],"DeepSeek-R1":[12,85],"and":[13,57,63,69,86,143,156,166],"OpenAI's":[14,115],"o1,":[15],"show":[16,98],"that":[17,99],"extending":[18],"the":[19,31,47,94,150,164],"chain":[20],"thought":[22],"during":[23],"inference":[24],"can":[25],"significantly":[26],"improve":[27],"general":[28],"reasoning":[29,38,81],"performance.However,":[30],"impact":[32],"this":[34,43],"paradigm":[35],"on":[36,120],"legal":[37,65,80,95,112,136,141],"remains":[39],"insufficiently":[40],"explored.To":[41],"address":[42],"gap,":[44],"we":[45,73],"present":[46],"first":[48],"systematic":[49],"evaluation":[50],"12":[52],"LLMs,":[53],"including":[54],"both":[55],"reasoning-focused":[56],"general-purpose":[58],"models,":[59],"across":[60,104],"17":[61],"Chinese":[62,111],"English":[64,121],"tasks":[66],"spanning":[67],"statutory":[68],"caselaw":[70],"traditions.In":[71],"addition,":[72],"curate":[74],"a":[75,125],"bilingual":[76],"chain-of-thought":[77],"dataset":[78,165],"for":[79,93,140,160],"through":[82],"distillation":[83],"from":[84],"develop":[87],"Legal-R1,":[88],"an":[89],"open-source":[90],"model":[91,167],"specialized":[92],"domain.Experimental":[96],"results":[97,119],"Legal-R1":[100],"delivers":[101],"competitive":[102],"performance":[103],"diverse":[105],"tasks.DeepSeek-R1":[106],"exhibits":[107],"clear":[108],"advantages":[109],"reasoning,":[113],"while":[114],"o1":[116],"achieves":[117],"comparable":[118],"tasks.We":[122],"further":[123],"conduct":[124],"detailed":[126],"error":[127],"analysis,":[128],"which":[129],"reveals":[130],"recurring":[131],"issues":[132],"such":[133],"as":[134],"outdated":[135],"knowledge,":[137],"limited":[138],"capacity":[139],"interpretation,":[142],"susceptibility":[144],"to":[145],"factual":[146],"hallucinations.These":[147],"findings":[148],"delineate":[149],"main":[151],"obstacles":[152],"confronting":[153],"legal-domain":[154],"LLMs":[155],"suggest":[157],"promising":[158],"directions":[159],"future":[161],"research.We":[162],"release":[163],"at":[168],"https:":[169],"//github.com/YinghaoHu/Legal-R1-14B.":[170]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}