{"id":"https://openalex.org/W4416034105","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.968","title":"Semantic-Aware Action Space Compression via LLM-DRL Synergy for Efficient Task-oriented Dialogue Policy Exploration","display_name":"Semantic-Aware Action Space Compression via LLM-DRL Synergy for Efficient Task-oriented Dialogue Policy Exploration","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034105","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.968"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.968","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.968","pdf_url":"https://aclanthology.org/2025.findings-emnlp.968.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.968.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103015387","display_name":"Yangyang Zhao","orcid":"https://orcid.org/0000-0003-1890-6508"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yangyang Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029380465","display_name":"Ben Niu","orcid":"https://orcid.org/0000-0002-3680-5594"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ben Niu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106403476","display_name":"Yuxuan Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Tan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107808323","display_name":"Shihan Wang","orcid":"https://orcid.org/0000-0001-5971-7522"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shihan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5029082837","display_name":"Libo Qin","orcid":"https://orcid.org/0000-0002-3619-675X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Libo Qin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.16988902,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17808","last_page":"17820"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.7547000050544739,"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/T12031","display_name":"Speech and dialogue systems","score":0.7547000050544739,"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/T10028","display_name":"Topic Modeling","score":0.07850000262260437,"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":0.026100000366568565,"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":0.5235999822616577},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.42820000648498535},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.39590001106262207},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3718000054359436},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.310699999332428}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5989999771118164},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5235999822616577},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.42820000648498535},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3034000098705292},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2637999951839447},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.23770000040531158}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.968","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.968","pdf_url":"https://aclanthology.org/2025.findings-emnlp.968.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.library.uu.nl:1874/483471","is_oa":true,"landing_page_url":"https://dspace.library.uu.nl/handle/1874/483471","pdf_url":null,"source":{"id":"https://openalex.org/S4306401649","display_name":"Utrecht University Repository (Utrecht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193662353","host_organization_name":"Utrecht University","host_organization_lineage":["https://openalex.org/I193662353"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Part of book"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.968","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.968","pdf_url":"https://aclanthology.org/2025.findings-emnlp.968.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322843","display_name":"Natural Science Foundation of\u00a0Hunan Province","ror":null},{"id":"https://openalex.org/F4320335581","display_name":"Young Scientists Fund","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034105.pdf","grobid_xml":"https://content.openalex.org/works/W4416034105.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"flexibility":[1],"of":[2,67,77,141,149],"natural":[3],"language":[4,28],"significantly":[5],"expands":[6],"the":[7,61,118,138,147],"action":[8,74,98,104],"space":[9],"in":[10,20,90],"task-oriented":[11],"dialogue":[12,115],"systems,":[13],"causing":[14],"inefficient":[15],"exploration":[16,123],"and":[17,34,64],"slow":[18],"convergence":[19],"deep":[21],"reinforcement":[22],"learning":[23],"(DRL)-based":[24],"policy":[25],"optimization.Pretrained":[26],"large":[27],"models":[29],"(LLMs),":[30],"with":[31,58],"world":[32,62],"knowledge":[33,63],"semantic":[35],"understanding,":[36],"offer":[37],"promising":[38],"solutions.To":[39],"this":[40],"end,":[41],"we":[42],"propose":[43],"LLM-Guided":[44],"DRL":[45,119],"via":[46,72],"Semantic-Aware":[47],"Action":[48],"Pruning":[49],"(LLMSAP),":[50],"a":[51,96,125],"novel":[52],"framework":[53,130],"that":[54],"synergizes":[55],"pretrained":[56],"LLMs":[57,68,79,101],"DRL.LLMSAP":[59],"leverages":[60],"contextual":[65],"understanding":[66],"to":[69,80,86,121],"guide":[70],"decision-making":[71,139],"an":[73],"feasibility":[75],"assessment.Instead":[76],"requiring":[78],"directly":[81],"generate":[82],"optimal":[83],"actions":[84,112],"due":[85],"their":[87],"limited":[88],"precision":[89,140],"sequential":[91],"decision":[92],"tasks,":[93],"LLMSAP":[94],"employs":[95],"lightweight":[97],"pruning":[99],"mechanism.Specifically,":[100],"act":[102],"as":[103],"filters,":[105],"rapidly":[106],"eliminating":[107],"semantically":[108],"implausible":[109],"or":[110],"low-potential":[111],"from":[113],"multi-turn":[114],"context,":[116],"allowing":[117],"agent":[120],"focus":[122],"on":[124,143],"refined":[126],"candidate":[127],"subset.This":[128],"two-stage":[129],"(\"prune-thenoptimize\")":[131],"avoids":[132],"extensive":[133],"LLM":[134],"fine-tuning":[135],"while":[136],"preserving":[137],"DRL.Experiments":[142],"multiple":[144],"benchmarks":[145],"verify":[146],"effectiveness":[148],"LLMSAP.":[150]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-11-08T00:00:00"}