{"id":"https://openalex.org/W7224313640","doi":"https://doi.org/10.18653/2026.findings-emnlp.907","title":"ChapterRL: Chapter-Aware Reward Framework for Novel Generation Reinforcement Learning","display_name":"ChapterRL: Chapter-Aware Reward Framework for Novel Generation Reinforcement Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7224313640","doi":"https://doi.org/10.18653/2026.findings-emnlp.907"},"language":"en","primary_location":{"id":"doi:10.18653/2026.findings-emnlp.907","doi":"https://doi.org/10.18653/2026.findings-emnlp.907","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.907","pdf_url":"https://aclanthology.org/2026.findings-emnlp.907.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.findings-emnlp.907.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160085880","display_name":"Bingqian Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingqian Sun","raw_affiliation_strings":["Kuaishou Technology ,","Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology ,","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160148501","display_name":"Jingchao Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingchao Yang","raw_affiliation_strings":["Kuaishou Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology ,","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160084037","display_name":"Xiangyu Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Wu","raw_affiliation_strings":["Kuaishou Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology ,","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160122711","display_name":"Zhang Yunfei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang Yunfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139808349","display_name":"Tingting Gao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingting Gao","raw_affiliation_strings":["Kuaishou Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology ,","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101277553","display_name":"Han Li","orcid":"https://orcid.org/0000-0001-9368-826X","observed_orcids":["https://orcid.org/0000-0001-9368-826X"]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Li","raw_affiliation_strings":["Kuaishou Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology ,","institution_ids":["https://openalex.org/I4401726859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.89296763,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19206","last_page":"19223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5557000041007996,"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":0.5557000041007996,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.20029999315738678,"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":0.07339999824762344,"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/reinforcement-learning","display_name":"reinforcement learning","score":0.7400000095367432},{"id":"https://openalex.org/keywords/reward-function-design","display_name":"reward function design","score":0.44999998807907104},{"id":"https://openalex.org/keywords/text-generation","display_name":"text generation","score":0.5040000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5565000176429749},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5307999849319458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5013999938964844},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2635999917984009},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/2026.findings-emnlp.907","doi":"https://doi.org/10.18653/2026.findings-emnlp.907","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.907","pdf_url":"https://aclanthology.org/2026.findings-emnlp.907.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/2026.findings-emnlp.907","doi":"https://doi.org/10.18653/2026.findings-emnlp.907","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.907","pdf_url":"https://aclanthology.org/2026.findings-emnlp.907.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224313640.pdf","grobid_xml":"https://content.openalex.org/works/W7224313640.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2802035631","https://openalex.org/W7166808858","https://openalex.org/W4416036697","https://openalex.org/W7166811697","https://openalex.org/W7224436734","https://openalex.org/W7224448149","https://openalex.org/W7166834202","https://openalex.org/W6885068755","https://openalex.org/W4412944949","https://openalex.org/W4385674827"],"abstract_inverted_index":{"Multi-chapter":[0],"novel":[1],"generation":[2,45],"requires":[3],"models":[4],"to":[5,31,82,101],"balance":[6],"two":[7,53,98],"quality":[8,63,146],"dimensions":[9],"simultaneously:":[10],"chapter-level":[11,62],"reader":[12,38,66],"engagement":[13],"and":[14,25,37,68,104,108,125,147,153],"global":[15,105],"narrative":[16,106,134,160],"rhythm.Existing":[17],"approaches":[18],"have":[19],"mainly":[20],"focused":[21],"on":[22,87,121,132],"planning,":[23],"memory,":[24],"execution,":[26],"while":[27,156],"paying":[28],"limited":[29],"attention":[30],"the":[32,92,117,137],"mismatch":[33],"between":[34],"training":[35],"signals":[36,64,99],"experience.We":[39],"propose":[40],"Chap-terRL,":[41],"which":[42],"reformulates":[43],"multi-chapter":[44],"as":[46,163],"a":[47,84,96],"reward":[48,55,130,167],"design":[49],"problem.Specifically,":[50],"ChapterRL":[51,119],"introduces":[52],"complementary":[54],"signals.Reading":[56],"Depth":[57],"Residual":[58],"(RDR)":[59],"derives":[60],"debiased":[61],"from":[65],"continuation":[67],"completion":[69],"behavior":[70],"through":[71],"genre-position":[72],"stratified":[73],"normalization.Dynamic":[74],"Rhythm":[75],"Trajectory":[76],"(DRT)":[77],"uses":[78],"an":[79,164],"arousal":[80],"estimator":[81],"impose":[83],"threshold-gated":[85],"penalty":[86],"systematic":[88],"rhythm":[89,148],"collapse":[90],"in":[91],"later":[93],"part":[94],"of":[95,136],"story.The":[97],"correspond":[100],"chapter":[102,145],"attractiveness":[103],"momentum,":[107],"are":[109],"jointly":[110],"integrated":[111],"into":[112],"reinforcement":[113],"learning":[114],"training.We":[115],"evaluate":[116],"full":[118],"policy":[120],"three":[122],"automatic":[123],"benchmarks":[124],"separately":[126],"validate":[127],"its":[128],"RDR":[129,157],"model":[131],"taskaligned":[133],"domains":[135],"Chinese":[138],"Writ-ingPreferenceBench.":[139],"Results":[140],"show":[141],"that":[142],"Chap-terRL":[143],"improves":[144],"stability":[149],"over":[150],"supervised":[151],"fine-tuning":[152],"singlereward":[154],"variants,":[155],"exhibits":[158],"strong":[159],"preference":[161],"alignment":[162],"efficient":[165],"scalar":[166],"model.Code":[168],"is":[169],"available":[170],"at":[171],"Chap-":[172],"terRL.":[173]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-10-30T00:00:00"}