{"id":"https://openalex.org/W7119935237","doi":"https://doi.org/10.18653/2026.emnlp-main.676","title":"Gavel: Agent Meets Checklist for Evaluating LLMs on Long-Context Legal Summarization","display_name":"Gavel: Agent Meets Checklist for Evaluating LLMs on Long-Context Legal Summarization","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7119935237","doi":"https://doi.org/10.18653/2026.emnlp-main.676"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.676","doi":"https://doi.org/10.18653/2026.emnlp-main.676","is_oa":false,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.676","pdf_url":null,"source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.04424","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138047946","display_name":"Yao Dou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao Dou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144314241","display_name":"Benjamin Mamut","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benjamin Mamut","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5121024137","display_name":"Wei Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Xu","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03234209,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15553","last_page":"15603"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.8920999765396118,"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":0.8920999765396118,"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":0.10300000011920929,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0006000000284984708,"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/large-language-models","display_name":"large language models","score":0.7229999899864197},{"id":"https://openalex.org/keywords/multi-document-summarization","display_name":"multi-document summarization","score":0.9580000042915344},{"id":"https://openalex.org/keywords/hallucinations","display_name":"hallucinations","score":0.8379999995231628},{"id":"https://openalex.org/keywords/assessment-checklist","display_name":"evaluation checklist","score":0.5770000219345093},{"id":"https://openalex.org/keywords/token-efficiency","display_name":"token efficiency","score":0.6190000176429749},{"id":"https://openalex.org/keywords/manual-annotation","display_name":"manual annotation","score":0.48399999737739563}],"concepts":[{"id":"https://openalex.org/C2779356329","wikidata":"https://www.wikidata.org/wiki/Q922625","display_name":"Checklist","level":2,"score":0.7591999769210815},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7077999711036682},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4580000042915344},{"id":"https://openalex.org/C37381756","wikidata":"https://www.wikidata.org/wiki/Q20203288","display_name":"Representativeness heuristic","level":2,"score":0.445499986410141},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4056999981403351},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40290001034736633},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3693999946117401},{"id":"https://openalex.org/C16678853","wikidata":"https://www.wikidata.org/wiki/Q486972","display_name":"Human settlement","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C168725872","wikidata":"https://www.wikidata.org/wiki/Q991663","display_name":"Sophistication","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3246000111103058},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.30379998683929443},{"id":"https://openalex.org/C39549134","wikidata":"https://www.wikidata.org/wiki/Q133080","display_name":"Public relations","level":1,"score":0.30079999566078186},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.28949999809265137},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2766999900341034},{"id":"https://openalex.org/C75630572","wikidata":"https://www.wikidata.org/wiki/Q538904","display_name":"Applied psychology","level":1,"score":0.27480000257492065},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.27379998564720154},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.2612999975681305},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.2590000033378601},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2533999979496002}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.emnlp-main.676","doi":"https://doi.org/10.18653/2026.emnlp-main.676","is_oa":false,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.676","pdf_url":null,"source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2601.04424","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.04424","pdf_url":"https://arxiv.org/pdf/2601.04424","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.2601.04424","doi":"https://doi.org/10.48550/arxiv.2601.04424","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.04424","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:2601.04424","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.04424","pdf_url":"https://arxiv.org/pdf/2601.04424","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":[{"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5473999977111816}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4406052358","https://openalex.org/W7221751238","https://openalex.org/W4403103210","https://openalex.org/W7137901058","https://openalex.org/W4416988068","https://openalex.org/W7158208954","https://openalex.org/W4403943134","https://openalex.org/W7138029610","https://openalex.org/W4402648521","https://openalex.org/W4407123627"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,84],"(LLMs)":[3],"now":[4],"support":[5],"contexts":[6],"of":[7,54,130],"up":[8],"to":[9,88,142,154],"1M":[10],"tokens,":[11],"but":[12,106],"their":[13],"strengths":[14],"and":[15,63,66,110,144],"weaknesses":[16],"on":[17,28,98],"complex":[18,111],"long-context":[19],"tasks":[20],"remain":[21],"unclear.":[22],"To":[23,123],"study":[24],"this,":[25],"we":[26,126],"focus":[27],"multi-document":[29],"legal":[30],"case":[31,36,120],"summarization,":[32],"where":[33],"a":[34,56,68],"single":[35],"often":[37],"spans":[38],"many":[39],"documents":[40],"exceeding":[41],"100K":[42],"tokens.":[43,166],"We":[44],"systematically":[45],"evaluate":[46],"12":[47],"frontier":[48],"LLMs":[49],"with":[50,60,108,161],"Gavel,":[51,125],"which":[52],"consists":[53],"Gavel-Ref,":[55],"reference-based":[57],"evaluation":[58],"framework":[59],"checklist,":[61],"residual-fact,":[62],"writing-style":[64],"evaluations,":[65],"Gavel-Agent,":[67],"reference-free":[69],"agent":[70],"for":[71],"evaluating":[72],"factual":[73],"coverage":[74],"directly":[75],"from":[76],"source":[77],"documents.":[78],"Our":[79],"results":[80],"show":[81],"that":[82],"current":[83],"are":[85],"more":[86],"prone":[87],"omitting":[89],"key":[90],"information":[91],"than":[92],"hallucinating.":[93],"They":[94],"all":[95],"perform":[96],"well":[97],"simple":[99],"checklist":[100],"items,":[101,112],"such":[102,113],"as":[103,114,119],"filing":[104],"date,":[105],"struggle":[107],"rare":[109],"settlements.":[115],"Performance":[116],"also":[117,152],"declines":[118],"length":[121],"increases.":[122],"meta-evaluate":[124],"collect":[127],"160":[128],"hours":[129],"human":[131],"annotations.":[132],"Gavel-Agent":[133,151],"reduces":[134],"token":[135],"usage":[136],"by":[137],"at":[138,162],"least":[139,163],"36%":[140],"compared":[141],"end-to-end":[143],"chunk-by-chunk":[145],"methods":[146],"while":[147],"achieving":[148],"competitive":[149],"performance.":[150],"generalizes":[153],"the":[155,159],"medical":[156],"domain,":[157],"performing":[158],"best":[160],"77%":[164],"fewer":[165]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2026-01-10T00:00:00"}