{"id":"https://openalex.org/W4387323904","doi":"https://doi.org/10.48550/arxiv.2310.00785","title":"BooookScore: A systematic exploration of book-length summarization in the era of LLMs","display_name":"BooookScore: A systematic exploration of book-length summarization in the era of LLMs","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4387323904","doi":"https://doi.org/10.48550/arxiv.2310.00785"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.00785","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.00785","pdf_url":"https://arxiv.org/pdf/2310.00785","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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/2310.00785","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080987186","display_name":"Yapei Chang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chang, Yapei","raw_affiliation_strings":["University of Massachusetts Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066588555","display_name":"Kyle Lo","orcid":"https://orcid.org/0000-0002-1804-2853","observed_orcids":["https://orcid.org/0000-0002-1804-2853"]},"institutions":[{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lo, Kyle","raw_affiliation_strings":["Allen Institute for AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for AI","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020127239","display_name":"Tanya Goyal","orcid":"https://orcid.org/0009-0009-6429-278X","observed_orcids":["https://orcid.org/0009-0009-6429-278X"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Goyal, Tanya","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082767919","display_name":"Mohit Iyyer","orcid":"https://orcid.org/0000-0001-7340-0804","observed_orcids":["https://orcid.org/0000-0001-7340-0804"]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Iyyer, Mohit","raw_affiliation_strings":["University of Massachusetts Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":18,"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":0.9731000065803528,"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":0.9731000065803528,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.014100000262260437,"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":0.0052999998442828655,"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":0.8460000157356262},{"id":"https://openalex.org/keywords/automatic-evaluation-metrics","display_name":"automatic evaluation metrics","score":0.5649999976158142},{"id":"https://openalex.org/keywords/gpt-4","display_name":"GPT-4","score":0.7390000224113464},{"id":"https://openalex.org/keywords/llama-2","display_name":"Llama 2","score":0.7419999837875366},{"id":"https://openalex.org/keywords/mixtral","display_name":"Mixtral","score":0.8579999804496765}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8463269472122192},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6920774579048157},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.5685924291610718},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4627516269683838},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.44717997312545776},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4241049587726593},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42375797033309937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3861047625541687},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3134339451789856},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.13166329264640808},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09583944082260132},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2310.00785","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.00785","pdf_url":"https://arxiv.org/pdf/2310.00785","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2310.00785","doi":"https://doi.org/10.48550/arxiv.2310.00785","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.00785","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.00785","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.00785","pdf_url":"https://arxiv.org/pdf/2310.00785","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1613569390","display_name":"Collaborative Research: STEM Learning Embedded in a Machine-in-the-Loop Collaborative Story Writing Game","funder_award_id":"2202506","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2601536509","display_name":"CAREER: Building Creative Writing Assistants for Machine-in-the-Loop Storytelling","funder_award_id":"2046248","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320315389","display_name":"Open Philanthropy Project","ror":"https://ror.org/004d1k391"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387323904.pdf","grobid_xml":"https://content.openalex.org/works/W4387323904.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7135095460","https://openalex.org/W4415883672","https://openalex.org/W4415063197","https://openalex.org/W4393903977","https://openalex.org/W7140115281","https://openalex.org/W6960423337","https://openalex.org/W7158208954","https://openalex.org/W4403296360","https://openalex.org/W4404782477","https://openalex.org/W4415524169"],"abstract_inverted_index":{"Summarizing":[0],"book-length":[1,59,99],"documents":[2],"(>100K":[3],"tokens)":[4],"that":[5,156,165,213],"exceed":[6],"the":[7,19,38,54,66,91,95,158,171,188],"context":[8],"window":[9],"size":[10],"of":[11,42,56,69,94,97,128,137,160,170,190,255],"large":[12],"language":[13],"models":[14],"(LLMs)":[15],"requires":[16],"first":[17,92],"breaking":[18],"input":[20],"document":[21],"into":[22],"smaller":[23],"chunks":[24],"and":[25,33,40,73,111,132,148,182,204,219],"then":[26],"prompting":[27,104],"an":[28,152],"LLM":[29,84],"to":[30,48,53,78,185],"merge,":[31],"update,":[32],"compress":[34],"chunk-level":[35,109],"summaries.":[36],"Despite":[37],"complexity":[39],"importance":[41],"this":[43,87],"task,":[44],"it":[45],"has":[46,176],"yet":[47],"be":[49],"meaningfully":[50],"studied":[51],"due":[52],"challenges":[55],"evaluation:":[57],"existing":[58,74],"summarization":[60],"datasets":[61],"(e.g.,":[62,195],"BookSum)":[63],"are":[64],"in":[65,162,207],"pretraining":[67],"data":[68],"most":[70],"public":[71],"LLMs,":[72],"evaluation":[75,145,209],"methods":[76],"struggle":[77],"capture":[79],"errors":[80,139],"made":[81,140],"by":[82,141,230,264],"modern":[83],"summarizers.":[85],"In":[86],"paper,":[88],"we":[89,150],"present":[90],"study":[93],"coherence":[96,138],"LLM-based":[98],"summarizers":[100],"implemented":[101],"via":[102],"two":[103],"workflows:":[105],"(1)":[106],"hierarchically":[107],"merging":[108],"summaries,":[110],"(2)":[112],"incrementally":[113],"updating":[114,248],"a":[115,163,260],"running":[116],"summary.":[117],"We":[118,211],"obtain":[119],"1193":[120],"fine-grained":[121],"human":[122,144,180,208],"annotations":[123,181],"on":[124,243],"GPT-4":[125,218],"generated":[126,229],"summaries":[127,223],"100":[129],"recently-published":[130],"books":[131],"identify":[133],"eight":[134],"common":[135],"types":[136],"LLMs.":[142],"Because":[143],"is":[146],"expensive":[147],"time-consuming,":[149],"develop":[151],"automatic":[153],"metric,":[154],"BooookScore,":[155],"measures":[157],"proportion":[159],"sentences":[161],"summary":[164],"do":[166],"not":[167],"contain":[168],"any":[169],"identified":[172],"error":[173],"types.":[174],"BooookScore":[175,226,251],"high":[177],"agreement":[178],"with":[179,224,245],"allows":[183],"us":[184],"systematically":[186],"evaluate":[187],"impact":[189],"many":[191],"other":[192,238],"critical":[193],"parameters":[194],"chunk":[196],"size,":[197],"base":[198],"LLM)":[199],"while":[200],"saving":[201],"$15K":[202],"USD":[203],"500":[205],"hours":[206],"costs.":[210],"find":[212],"closed-source":[214],"LLMs":[215],"such":[216],"as":[217],"Claude":[220],"2":[221,235],"produce":[222],"higher":[225,253],"than":[227,257],"those":[228],"open-source":[231],"models.":[232],"While":[233],"LLaMA":[234],"falls":[236],"behind":[237],"models,":[239],"Mixtral":[240],"achieves":[241],"performance":[242],"par":[244],"GPT-3.5-Turbo.":[246],"Incremental":[247],"yields":[249],"lower":[250],"but":[252],"level":[254],"detail":[256],"hierarchical":[258],"merging,":[259],"trade-off":[261],"sometimes":[262],"preferred":[263],"annotators.":[265]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2023-10-04T00:00:00"}