{"id":"https://openalex.org/W7166825614","doi":"https://doi.org/10.18653/v1/2026.acl-long.2019","title":"PodBench: A Comprehensive Benchmark for Instruction-Aware Audio-Oriented Podcast Script Generation","display_name":"PodBench: A Comprehensive Benchmark for Instruction-Aware Audio-Oriented Podcast Script Generation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166825614","doi":"https://doi.org/10.18653/v1/2026.acl-long.2019"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.2019","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2019","pdf_url":"https://aclanthology.org/2026.acl-long.2019.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.2019.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139842850","display_name":"Chenning Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenning Xu","raw_affiliation_strings":["Large Language Model Department , Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Large Language Model Department , Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050256868","display_name":"Mao Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mao Zheng","raw_affiliation_strings":["Large Language Model Department , Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Large Language Model Department , Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014223736","display_name":"Mingyu Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyu Zheng","raw_affiliation_strings":["Large Language Model Department , Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Large Language Model Department , Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101517822","display_name":"Mingyang Song","orcid":"https://orcid.org/0009-0002-5354-7045"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyang Song","raw_affiliation_strings":["Large Language Model Department , Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Large Language Model Department , Tencent","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.96826571,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"43605","last_page":"43621"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12354","display_name":"Innovations in Educational Methods","score":0.22280000150203705,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"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/T12354","display_name":"Innovations in Educational Methods","score":0.22280000150203705,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"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/T12720","display_name":"Multimedia Communication and Technology","score":0.12460000067949295,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.08990000188350677,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/benchmark","display_name":"Benchmark (surveying)","score":0.5349000096321106},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.30379998683929443},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.27970001101493835},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2727999985218048}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7486000061035156},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5349000096321106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40959998965263367},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38839998841285706},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3449999988079071},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3287999927997589},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.27970001101493835},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.2019","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2019","pdf_url":"https://aclanthology.org/2026.acl-long.2019.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.2019","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2019","pdf_url":"https://aclanthology.org/2026.acl-long.2019.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7617288827896118,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166825614.pdf","grobid_xml":"https://content.openalex.org/works/W7166825614.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Podcast":[0],"script":[1,111],"generation":[2],"requires":[3],"LLMs":[4],"to":[5,36,81,104],"synthesize":[6],"structured,":[7],"context-grounded":[8],"dialogue":[9],"from":[10],"diverse":[11],"inputs,":[12],"yet":[13],"systematic":[14],"evaluation":[15,46],"resources":[16],"for":[17],"this":[18,23],"task":[19],"remain":[20],"limited.To":[21],"bridge":[22],"gap,":[24],"we":[25],"introduce":[26],"PodBench,":[27],"a":[28,44,87,101],"benchmark":[29],"comprising":[30],"800":[31],"samples":[32],"with":[33,52,67],"inputs":[34],"up":[35],"21K":[37],"tokens":[38],"and":[39,77,114],"complex":[40],"multi-speaker":[41,78],"instructions.We":[42],"propose":[43],"multifaceted":[45],"framework":[47],"that":[48,58],"integrates":[49],"quantitative":[50],"constraints":[51],"LLM-based":[53],"quality":[54],"assessment.Extensive":[55],"experiments":[56],"reveal":[57],"while":[59],"proprietary":[60],"models":[61,65],"generally":[62],"excel,":[63],"open-source":[64],"equipped":[66],"explicit":[68],"reasoning":[69],"demonstrate":[70],"superior":[71],"robustness":[72],"in":[73,108],"handling":[74],"long":[75],"contexts":[76],"coordination":[79],"compared":[80],"standard":[82],"baselines.However,":[83],"our":[84],"analysis":[85],"uncovers":[86],"persistent":[88],"divergence":[89],"where":[90],"high":[91,97],"instruction":[92],"following":[93],"does":[94],"not":[95],"guarantee":[96],"content":[98],"substance.PodBench":[99],"offers":[100],"reproducible":[102],"testbed":[103],"address":[105],"these":[106],"challenges":[107],"long-form,":[109],"audio-centric":[110],"generation.The":[112],"code":[113],"data":[115],"are":[116],"publicly":[117],"accessible":[118],"here.":[119]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}