{"id":"https://openalex.org/W4386651352","doi":"https://doi.org/10.48550/arxiv.2309.05196","title":"Does Writing with Language Models Reduce Content Diversity?","display_name":"Does Writing with Language Models Reduce Content Diversity?","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386651352","doi":"https://doi.org/10.48550/arxiv.2309.05196"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2309.05196","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.05196","pdf_url":"https://arxiv.org/pdf/2309.05196","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":"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/2309.05196","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052649262","display_name":"Vishakh Padmakumar","orcid":"https://orcid.org/0000-0002-3396-3589","observed_orcids":["https://orcid.org/0000-0002-3396-3589"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Padmakumar, Vishakh","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100775952","display_name":"He He","orcid":"https://orcid.org/0000-0002-9118-2449","observed_orcids":["https://orcid.org/0000-0002-9118-2449","https://orcid.org/0009-0005-7805-3780"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":21,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.4950999915599823,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.4950999915599823,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"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":0.18330000340938568,"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":0.0746999979019165,"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":0.9660000205039978},{"id":"https://openalex.org/keywords/collaborative-writing","display_name":"collaborative writing","score":0.7570000290870667},{"id":"https://openalex.org/keywords/content-diversity","display_name":"content diversity","score":0.781000018119812},{"id":"https://openalex.org/keywords/argumentative-essay","display_name":"argumentative essay","score":0.7350000143051147},{"id":"https://openalex.org/keywords/gpt-3","display_name":"GPT-3","score":0.8389999866485596},{"id":"https://openalex.org/keywords/lexical-diversity","display_name":"lexical diversity","score":0.8960000276565552},{"id":"https://openalex.org/keywords/text-similarity","display_name":"text similarity","score":0.5350000262260437},{"id":"https://openalex.org/keywords/human-ai-collaboration","display_name":"human-AI collaboration","score":0.6209999918937683},{"id":"https://openalex.org/keywords/diversity-index","display_name":"diversity indices","score":0.6349999904632568}],"concepts":[{"id":"https://openalex.org/C2781306805","wikidata":"https://www.wikidata.org/wiki/Q4789761","display_name":"Argumentative","level":2,"score":0.8534096479415894},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.7604776620864868},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.6400036811828613},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6053097248077393},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.6004961133003235},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5782109498977661},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5730615854263306},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.4924803674221039},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44022083282470703},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4312707185745239},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.40432095527648926},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.36822354793548584},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3322433531284332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3156573176383972},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.2442774474620819},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1521616280078888},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11710125207901001},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0972486138343811},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.07791793346405029},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2309.05196","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.05196","pdf_url":"https://arxiv.org/pdf/2309.05196","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2309.05196","doi":"https://doi.org/10.48550/arxiv.2309.05196","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2309.05196","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:2309.05196","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.05196","pdf_url":"https://arxiv.org/pdf/2309.05196","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.699999988079071,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G1338796077","display_name":"CAREER: Enhancing Diversity and Personalization in Human-AI Collaborative Writing","funder_award_id":"2340345","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5693414920","display_name":"NRT-HDR: FUTURE Foundations, Translation, and Responsibility for Data Science Impact","funder_award_id":"1922658","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/W4386651352.pdf","grobid_xml":"https://content.openalex.org/works/W4386651352.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4407695828","https://openalex.org/W4417089508","https://openalex.org/W7204139224","https://openalex.org/W4417271155","https://openalex.org/W4416036410","https://openalex.org/W4414938331","https://openalex.org/W4416455530","https://openalex.org/W7125775143","https://openalex.org/W4404395419","https://openalex.org/W7009647823"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,163],"(LLMs)":[3],"have":[4],"led":[5],"to":[6,133,139,164],"a":[7,26,54,67,71,82,99],"surge":[8],"in":[9,31,39,62,98,103,158],"collaborative":[10],"writing":[11,76,90],"with":[12,91],"model":[13,78,150],"assistance.":[14],"As":[15],"different":[16,114],"users":[17,58],"incorporate":[18],"suggestions":[19],"from":[20,161],"the":[21,32,47,95,108,111,118,144,155,170],"same":[22],"model,":[23],"there":[24],"is":[25,130],"risk":[27],"of":[28,49,84,113,172],"decreased":[29],"diversity":[30,52,85],"produced":[33],"content,":[34],"potentially":[35],"limiting":[36],"diverse":[37,137,177],"perspectives":[38],"public":[40],"discourse.":[41],"In":[42,142],"this":[43,128],"work,":[44],"we":[45],"measure":[46],"impact":[48],"co-writing":[50],"on":[51],"via":[53],"controlled":[55],"experiment,":[56],"where":[57],"write":[59],"argumentative":[60],"essays":[61],"three":[63],"setups":[64],"--":[65],"using":[66],"base":[68],"LLM":[69,73],"(GPT3),":[70],"feedback-tuned":[72],"(InstructGPT),":[74],"and":[75,87,116,121,175],"without":[77],"help.":[79],"We":[80,124],"develop":[81],"set":[83],"metrics":[86],"find":[88,126],"that":[89,127,154],"InstructGPT":[92,134],"(but":[93],"not":[94],"GPT3)":[96],"results":[97],"statistically":[100],"significant":[101],"reduction":[102],"diversity.":[104,123],"Specifically,":[105],"it":[106],"increases":[107],"similarity":[109],"between":[110],"writings":[112],"authors":[115],"reduces":[117],"overall":[119],"lexical":[120],"content":[122],"additionally":[125],"effect":[129],"mainly":[131],"attributable":[132],"contributing":[135],"less":[136,176],"text":[138,146],"co-written":[140],"essays.":[141],"contrast,":[143],"user-contributed":[145],"remains":[147],"unaffected":[148],"by":[149],"collaboration.":[151],"This":[152],"suggests":[153],"recent":[156],"improvement":[157],"generation":[159],"quality":[160],"adapting":[162],"human":[165],"feedback":[166],"might":[167],"come":[168],"at":[169],"cost":[171],"more":[173],"homogeneous":[174],"content.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2023-09-13T00:00:00"}