{"id":"https://openalex.org/W3207969408","doi":null,"title":"Boosting coherence of language models.","display_name":"Boosting coherence of language models.","publication_year":2021,"publication_date":"2021-10-15","ids":{"openalex":"https://openalex.org/W3207969408","mag":"3207969408"},"language":"en","primary_location":{"id":"mag:3207969408","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2110.08294.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.08294.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068089852","display_name":"Nikolay Malkin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikolay Malkin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422319","display_name":"Zhen Wang","orcid":"https://orcid.org/0000-0002-3399-5281","observed_orcids":["https://orcid.org/0000-0002-3399-5281","https://orcid.org/0000-0003-4808-2159"]},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhen Wang","raw_affiliation_strings":["Ohio State University"],"raw_orcid":"https://orcid.org/0000-0002-3399-5281","affiliations":[{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108373424","display_name":"Neboj\u0161a Joji\u0107","orcid":"https://orcid.org/0009-0009-7115-2267","observed_orcids":["https://orcid.org/0009-0009-7115-2267"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neboj\u0161a Joji\u0107","raw_affiliation_strings":["(Microsoft)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I1290206253"]}]}],"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":false,"cited_by_count":1,"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":0.9214000105857849,"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":0.9214000105857849,"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":0.05400000140070915,"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/T12031","display_name":"Speech and dialogue systems","score":0.014600000344216824,"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/long-text-generation","display_name":"long-form text generation","score":0.6819999814033508},{"id":"https://openalex.org/keywords/next-token-prediction","display_name":"next-token prediction","score":0.6899999976158142},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6389999985694885},{"id":"https://openalex.org/keywords/distributional-analysis","display_name":"distributional analysis","score":0.6060000061988831},{"id":"https://openalex.org/keywords/inference-procedures","display_name":"inference procedures","score":0.34299999475479126}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.8983057737350464},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.7240183353424072},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6873289942741394},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.608088493347168},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5874996185302734},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.49837231636047363},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4599131643772125},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.45492544770240784},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34102851152420044},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29769283533096313},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12674418091773987},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0837644636631012},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3207969408","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2110.08294.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3207969408","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2110.08294.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2006969979","https://openalex.org/W2024046085","https://openalex.org/W2028175314","https://openalex.org/W2064675550","https://openalex.org/W2078861931","https://openalex.org/W2101105183","https://openalex.org/W2130158090","https://openalex.org/W2133512280","https://openalex.org/W2145755360","https://openalex.org/W2157331557","https://openalex.org/W2158195707","https://openalex.org/W2170240176","https://openalex.org/W2251939518","https://openalex.org/W2466175319","https://openalex.org/W2473344385","https://openalex.org/W2626778328","https://openalex.org/W2794325560","https://openalex.org/W2890894339","https://openalex.org/W2890969459","https://openalex.org/W2946609015","https://openalex.org/W2948710720","https://openalex.org/W2963096510","https://openalex.org/W2963206148","https://openalex.org/W2963456134","https://openalex.org/W2963951265","https://openalex.org/W2963995027","https://openalex.org/W2964308564","https://openalex.org/W2970476646","https://openalex.org/W2996287690","https://openalex.org/W2997517014","https://openalex.org/W2998617917","https://openalex.org/W3015468748","https://openalex.org/W3026404337","https://openalex.org/W3045733172","https://openalex.org/W3103875432","https://openalex.org/W3132736064","https://openalex.org/W3157005959","https://openalex.org/W3166595320","https://openalex.org/W3173673636","https://openalex.org/W3174428931","https://openalex.org/W3192405822","https://openalex.org/W3196318247","https://openalex.org/W3212120741","https://openalex.org/W3212382565","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4285233740","https://openalex.org/W4386473595","https://openalex.org/W2899485151","https://openalex.org/W3162153998","https://openalex.org/W4385574023","https://openalex.org/W2963325985","https://openalex.org/W2963482033","https://openalex.org/W3167303745","https://openalex.org/W7212314043","https://openalex.org/W2411759152"],"abstract_inverted_index":{"Naturality":[0],"of":[1,32,49,59,68],"long-term":[2],"information":[3],"structure":[4],"--":[5,7],"coherence":[6,40,60,79],"remains":[8],"a":[9],"challenge":[10],"in":[11,30],"language":[12,15],"generation.":[13],"Large":[14],"models":[16,64,83],"have":[17],"insufficiently":[18],"learned":[19],"such":[20],"structure,":[21],"as":[22],"their":[23],"long-form":[24],"generations":[25],"differ":[26],"from":[27],"natural":[28],"text":[29,71],"measures":[31],"coherence.":[33],"To":[34],"alleviate":[35],"this":[36],"divergence,":[37],"we":[38],"propose":[39],"boosting,":[41],"an":[42],"inference":[43],"procedure":[44],"that":[45,78],"increases":[46],"the":[47,57],"effect":[48],"distant":[50],"context":[51],"on":[52],"next-token":[53],"prediction.":[54],"We":[55,75],"show":[56],"benefits":[58],"boosting":[61,80],"with":[62,81,92],"pretrained":[63],"by":[65],"distributional":[66],"analyses":[67],"generated":[69],"ordinary":[70],"and":[72],"dialog":[73],"responses.":[74],"also":[76],"find":[77],"state-of-the-art":[82],"for":[84],"various":[85],"zero-shot":[86],"NLP":[87],"tasks":[88],"yields":[89],"performance":[90],"gains":[91],"no":[93],"additional":[94],"training.":[95]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-10-25T00:00:00"}