{"id":"https://openalex.org/W4411528117","doi":"https://doi.org/10.1145/3735654.3735941","title":"Towards a Framework for Hierarchical Text Segmentation using Large Language Models","display_name":"Towards a Framework for Hierarchical Text Segmentation using Large Language Models","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4411528117","doi":"https://doi.org/10.1145/3735654.3735941"},"language":"en","primary_location":{"id":"doi:10.1145/3735654.3735941","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3735654.3735941","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3735654.3735941","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Data Management for End-to-End Machine Learning","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3735654.3735941","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003070287","display_name":"Lampros Flokas","orcid":"https://orcid.org/0000-0002-2496-3624"},"institutions":[{"id":"https://openalex.org/I4210098601","display_name":"Celsion (United States)","ror":"https://ror.org/00tzssk35","country_code":"US","type":"company","lineage":["https://openalex.org/I4210098601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lampros Flokas","raw_affiliation_strings":["Celonis, New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-2496-3624","affiliations":[{"raw_affiliation_string":"Celonis, New York, NY, USA","institution_ids":["https://openalex.org/I4210098601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103522493","display_name":"Jeffery Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098601","display_name":"Celsion (United States)","ror":"https://ror.org/00tzssk35","country_code":"US","type":"company","lineage":["https://openalex.org/I4210098601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffery Cao","raw_affiliation_strings":["Celonis, New York, NY, USA"],"raw_orcid":"https://orcid.org/0009-0002-6174-0902","affiliations":[{"raw_affiliation_string":"Celonis, New York, NY, USA","institution_ids":["https://openalex.org/I4210098601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042977565","display_name":"Yn Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098601","display_name":"Celsion (United States)","ror":"https://ror.org/00tzssk35","country_code":"US","type":"company","lineage":["https://openalex.org/I4210098601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yujian Xu","raw_affiliation_strings":["Celonis, New York, NY, USA"],"raw_orcid":"https://orcid.org/0009-0000-5046-8523","affiliations":[{"raw_affiliation_string":"Celonis, New York, NY, USA","institution_ids":["https://openalex.org/I4210098601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049016095","display_name":"Eugene Wu","orcid":"https://orcid.org/0000-0003-4254-6688"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Wu","raw_affiliation_strings":["Columbia University, Celonis, New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-4254-6688","affiliations":[{"raw_affiliation_string":"Columbia University, Celonis, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430982","display_name":"Xu Chu","orcid":"https://orcid.org/0009-0007-3202-3767"},"institutions":[{"id":"https://openalex.org/I4210098601","display_name":"Celsion (United States)","ror":"https://ror.org/00tzssk35","country_code":"US","type":"company","lineage":["https://openalex.org/I4210098601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu Chu","raw_affiliation_strings":["Celonis, New York, NY, USA"],"raw_orcid":"https://orcid.org/0009-0007-3202-3767","affiliations":[{"raw_affiliation_string":"Celonis, New York, NY, USA","institution_ids":["https://openalex.org/I4210098601"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107948168","display_name":"C. X. Yu","orcid":"https://orcid.org/0000-0001-6157-5797"},"institutions":[{"id":"https://openalex.org/I4210098601","display_name":"Celsion (United States)","ror":"https://ror.org/00tzssk35","country_code":"US","type":"company","lineage":["https://openalex.org/I4210098601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cong Yu","raw_affiliation_strings":["Celonis, New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0001-6157-5797","affiliations":[{"raw_affiliation_string":"Celonis, New York, NY, USA","institution_ids":["https://openalex.org/I4210098601"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"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":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9940999746322632,"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/computer-science","display_name":"Computer science","score":0.7802681922912598},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5921295881271362},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5465975403785706},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5217645764350891},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41304105520248413}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7802681922912598},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5921295881271362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5465975403785706},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5217645764350891},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41304105520248413}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3735654.3735941","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3735654.3735941","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3735654.3735941","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Data Management for End-to-End Machine Learning","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3735654.3735941","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3735654.3735941","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3735654.3735941","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Data Management for End-to-End Machine Learning","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411528117.pdf","grobid_xml":"https://content.openalex.org/works/W4411528117.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2150766729","https://openalex.org/W2596512067","https://openalex.org/W2962716111","https://openalex.org/W3034327408","https://openalex.org/W4386566495","https://openalex.org/W4391876619","https://openalex.org/W4401863388","https://openalex.org/W4402387139","https://openalex.org/W4403051598","https://openalex.org/W4403577657","https://openalex.org/W4406459892"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Thanks":[0],"to":[1,15,43,85,97],"the":[2,30,68,76,82,114,122,132,184,204],"in":[3,49,99],"context":[4],"learning":[5,197],"abilities":[6],"of":[7,52,62,79,110,124,186],"LLMs,":[8],"building":[9],"a":[10,40,57,60,88,106,155],"text":[11,137],"classifier":[12],"without":[13],"access":[14],"labeled":[16],"data":[17],"is":[18,36,95,105,147],"easier":[19],"than":[20,27],"ever.":[21],"However,":[22],"for":[23,135],"more":[24,101],"complex":[25],"tasks":[26],"simple":[28],"classification,":[29],"difficulties":[31],"remain.":[32],"One":[33],"such":[34,111],"task":[35],"hierarchical":[37,93,136,149,171],"segmentation":[38,94,138,150,172],"where":[39],"model":[41],"needs":[42],"break":[44],"down":[45],"an":[46,50],"input":[47,66,70],"document":[48,158],"hierarchy":[51],"segments":[53],"each":[54],"annotated":[55],"with":[56,87],"label":[58],"from":[59,201],"taxonomy":[61],"classes.":[63],"The":[64,141],"long":[65],"documents,":[67],"large":[69],"class":[71],"taxonomies":[72],"as":[73,75,154],"well":[74],"increased":[77],"number":[78],"outputs":[80],"make":[81],"problem":[83],"challenging":[84],"solve":[86],"single":[89],"LLM":[90],"call.":[91],"While":[92],"amenable":[96],"splitting":[98],"smaller":[100],"manageable":[102],"tasks,":[103],"there":[104],"huge":[107],"design":[108,205],"space":[109,206],"approaches":[112],"making":[113],"process":[115],"tedious":[116],"and":[117,128,159,177,191],"time":[118],"consuming.":[119],"To":[120],"reduce":[121],"amount":[123],"ad":[125],"hoc":[126],"exploration":[127],"implementation,":[129],"we":[130,166],"propose":[131,167],"first":[133],"framework":[134,146],"using":[139,207],"LLMs.":[140],"key":[142],"idea":[143],"behind":[144],"our":[145,208],"that":[148,195],"can":[151],"be":[152],"viewed":[153],"join":[156,163],"between":[157],"taxonomy.":[160],"Inspired":[161],"by":[162],"operator":[164],"design,":[165],"two":[168],"highly":[169],"configurable":[170],"algorithms":[173,190],"based":[174],"on":[175],"index":[176],"merge":[178],"sort":[179],"joins.":[180],"Our":[181],"experiments":[182],"highlight":[183],"existence":[185],"trade":[187],"offs":[188],"across":[189],"their":[192],"configurations,":[193],"indicating":[194],"machine":[196],"engineers":[198],"may":[199],"benefit":[200],"quickly":[202],"exploring":[203],"framework.":[209]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}