{"id":"https://openalex.org/W4416988064","doi":"https://doi.org/10.3233/faia251603","title":"Reinforcement Learning with Argument-Structured Reward for Court Decision Abstractive Summarization","display_name":"Reinforcement Learning with Argument-Structured Reward for Court Decision Abstractive Summarization","publication_year":2025,"publication_date":"2025-12-02","ids":{"openalex":"https://openalex.org/W4416988064","doi":"https://doi.org/10.3233/faia251603"},"language":null,"primary_location":{"id":"doi:10.3233/faia251603","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251603","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251603","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071314024","display_name":"Yuntao Kong","orcid":"https://orcid.org/0009-0001-2089-2363"},"institutions":[{"id":"https://openalex.org/I1284577377","display_name":"Center for Strategic and International Studies","ror":"https://ror.org/04my2jj52","country_code":"US","type":"other","lineage":["https://openalex.org/I1284577377"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuntao Kong","raw_affiliation_strings":["Center of Juris-Informatics, ROIS-DS, Japan"],"affiliations":[{"raw_affiliation_string":"Center of Juris-Informatics, ROIS-DS, Japan","institution_ids":["https://openalex.org/I1284577377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101737223","display_name":"Ye Xiong","orcid":"https://orcid.org/0000-0001-9770-6031"},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ye Xiong","raw_affiliation_strings":["Institute of Science Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo, Japan","institution_ids":["https://openalex.org/I4400009020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108319820","display_name":"Shuyuan Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuyuan Zheng","raw_affiliation_strings":["The University of Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Osaka, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103338430","display_name":"Ken Satoh","orcid":null},"institutions":[{"id":"https://openalex.org/I1284577377","display_name":"Center for Strategic and International Studies","ror":"https://ror.org/04my2jj52","country_code":"US","type":"other","lineage":["https://openalex.org/I1284577377"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ken Satoh","raw_affiliation_strings":["Center of Juris-Informatics, ROIS-DS, Japan"],"affiliations":[{"raw_affiliation_string":"Center of Juris-Informatics, ROIS-DS, Japan","institution_ids":["https://openalex.org/I1284577377"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5071314024"],"corresponding_institution_ids":["https://openalex.org/I1284577377"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.60099304,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.6345999836921692,"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":0.6345999836921692,"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/T13643","display_name":"Artificial Intelligence in Law","score":0.21819999814033508,"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":0.02979999966919422,"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/automatic-summarization","display_name":"Automatic summarization","score":0.9074000120162964},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7638000249862671},{"id":"https://openalex.org/keywords/argumentative","display_name":"Argumentative","score":0.6327999830245972},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5576000213623047},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.3303000032901764},{"id":"https://openalex.org/keywords/supreme-court","display_name":"Supreme court","score":0.3068000078201294}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9074000120162964},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7638000249862671},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7429999709129333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.680899977684021},{"id":"https://openalex.org/C2781306805","wikidata":"https://www.wikidata.org/wiki/Q4789761","display_name":"Argumentative","level":2,"score":0.6327999830245972},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5576000213623047},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5056999921798706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44269999861717224},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C2778272461","wikidata":"https://www.wikidata.org/wiki/Q190752","display_name":"Supreme court","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2953000068664551},{"id":"https://openalex.org/C2779525943","wikidata":"https://www.wikidata.org/wiki/Q1187300","display_name":"Grammaticality","level":3,"score":0.2660999894142151}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia251603","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251603","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia251603","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251603","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Court":[0,71],"decision":[1],"summarization":[2,23,33],"is":[3,91],"challenging":[4],"due":[5],"to":[6,45,95],"the":[7,68,85,92],"significant":[8],"length":[9],"and":[10,49,76],"structural":[11],"complexity":[12],"of":[13,87],"legal":[14,32,108],"documents,":[15],"which":[16],"makes":[17],"existing":[18],"reinforcement":[19],"learning":[20,61],"(RL)-based":[21],"abstractive":[22,31],"methods":[24],"less":[25],"effective.":[26],"We":[27],"propose":[28],"an":[29],"RL-based":[30,100],"model":[34,64],"with":[35,73],"a":[36,53,103],"novel":[37,104],"argument-structured":[38],"reward":[39],"mechanism.":[40],"It":[41],"leverages":[42],"Issue\u2013Reason\u2013Conclusion":[43],"components":[44],"compute":[46],"fine-grained":[47],"sub-rewards":[48],"aggregate":[50],"them":[51],"into":[52,99],"final":[54],"reward.":[55],"This":[56],"design":[57],"provides":[58],"more":[59],"reliable":[60],"signals":[62],"for":[63,106],"optimization.":[65],"Experiments":[66],"on":[67],"Indian":[69],"Supreme":[70],"dataset":[72],"Longformer-Encoder-Decoder":[74],"(LED)":[75],"Llama":[77],"demonstrate":[78],"consistent":[79],"improvements":[80],"over":[81],"non-argument-structured":[82],"methods.":[83],"To":[84],"best":[86],"our":[88],"knowledge,":[89],"this":[90],"first":[93],"work":[94],"incorporate":[96],"argumentative":[97],"structures":[98],"summarization,":[101],"offering":[102],"direction":[105],"improving":[107],"summarization.":[109]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-12-04T00:00:00"}