{"id":"https://openalex.org/W4416037163","doi":"https://doi.org/10.18653/v1/2025.emnlp-industry.129","title":"How Accurate Are LLMs at Multi-Question Answering on Conversational Transcripts?","display_name":"How Accurate Are LLMs at Multi-Question Answering on Conversational Transcripts?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416037163","doi":"https://doi.org/10.18653/v1/2025.emnlp-industry.129"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-industry.129","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-industry.129","pdf_url":"https://aclanthology.org/2025.emnlp-industry.129.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 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-industry.129.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033209447","display_name":"Xiliang Zhu","orcid":"https://orcid.org/0000-0001-9351-3005"},"institutions":[{"id":"https://openalex.org/I4210118121","display_name":"DIAL (Germany)","ror":"https://ror.org/02p6n7f90","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210118121"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Xiliang Zhu","raw_affiliation_strings":["Dialpad Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dialpad Inc","institution_ids":["https://openalex.org/I4210118121"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002606910","display_name":"Shi Zong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210118121","display_name":"DIAL (Germany)","ror":"https://ror.org/02p6n7f90","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210118121"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Shi Zong","raw_affiliation_strings":["Dialpad Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dialpad Inc","institution_ids":["https://openalex.org/I4210118121"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003655207","display_name":"David Rossouw","orcid":"https://orcid.org/0000-0003-2991-1812"},"institutions":[{"id":"https://openalex.org/I4210118121","display_name":"DIAL (Germany)","ror":"https://ror.org/02p6n7f90","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210118121"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"David Rossouw","raw_affiliation_strings":["Dialpad Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dialpad Inc","institution_ids":["https://openalex.org/I4210118121"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210118121"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29155324,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1848","last_page":"1855"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5655999779701233,"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":0.5655999779701233,"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":0.08089999854564667,"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/T13629","display_name":"Text Readability and Simplification","score":0.0608999989926815,"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/action","display_name":"Action (physics)","score":0.3102000057697296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42890000343322754},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.33500000834465027},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3336000144481659},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29019999504089355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2867000102996826},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.2824000120162964},{"id":"https://openalex.org/C39549134","wikidata":"https://www.wikidata.org/wiki/Q133080","display_name":"Public relations","level":1,"score":0.2669999897480011},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2542000114917755},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-industry.129","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-industry.129","pdf_url":"https://aclanthology.org/2025.emnlp-industry.129.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 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-industry.129","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-industry.129","pdf_url":"https://aclanthology.org/2025.emnlp-industry.129.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 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416037163.pdf","grobid_xml":"https://content.openalex.org/works/W4416037163.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deploying":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"for":[5,108],"question":[6],"answering":[7],"(QA)":[8],"over":[9],"lengthy":[10],"contexts":[11],"is":[12,20],"a":[13,64],"significant":[14],"challenge.In":[15],"industrial":[16],"settings,":[17],"this":[18,41,73],"process":[19],"often":[21],"hindered":[22],"by":[23],"high":[24],"computational":[25],"costs":[26],"and":[27,62,69,110],"latency,":[28],"especially":[29],"when":[30],"multiple":[31,51],"questions":[32,52],"must":[33],"be":[34],"answered":[35],"based":[36,53],"on":[37,54,72],"the":[38,45,55,86],"same":[39,56],"context.In":[40],"work,":[42],"we":[43],"explore":[44],"capabilities":[46],"of":[47,66],"LLMs":[48,82,92],"to":[49,95],"answer":[50],"conversational":[57],"context.We":[58],"conduct":[59],"extensive":[60],"experiments":[61],"benchmark":[63],"range":[65],"both":[67],"proprietary":[68,81],"public":[70,91],"models":[71],"challenging":[74],"task.Our":[75],"findings":[76],"highlight":[77],"that":[78],"while":[79],"strong":[80],"like":[83],"GPT-4o":[84,101],"achieve":[85],"best":[87],"overall":[88],"performance,":[89],"fine-tuned":[90],"with":[93],"up":[94],"8":[96],"billion":[97],"parameters":[98],"can":[99],"surpass":[100],"in":[102,113],"accuracy,":[103],"which":[104],"demonstrates":[105],"their":[106],"potential":[107],"transparent":[109],"cost-effective":[111],"deployment":[112],"real-world":[114],"applications.":[115]},"counts_by_year":[],"updated_date":"2026-08-24T07:32:12.397491","created_date":"2025-11-08T00:00:00"}