{"id":"https://openalex.org/W4404346653","doi":"https://doi.org/10.48550/arxiv.2410.23511","title":"Dynamic Strategy Planning for Efficient Question Answering with Large Language Models","display_name":"Dynamic Strategy Planning for Efficient Question Answering with Large Language Models","publication_year":2024,"publication_date":"2024-10-30","ids":{"openalex":"https://openalex.org/W4404346653","doi":"https://doi.org/10.48550/arxiv.2410.23511"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2410.23511","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.23511","pdf_url":"https://arxiv.org/pdf/2410.23511","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.23511","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067393636","display_name":"Tanmay Parekh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Parekh, Tanmay","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109295048","display_name":"Pradyot Prakash","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prakash, Pradyot","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107002940","display_name":"Alexander Radovic","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Radovic, Alexander","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114635417","display_name":"Akshay Shekher","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shekher, Akshay","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5036004105","display_name":"Denis Savenkov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Savenkov, Denis","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":null,"has_fulltext":true,"cited_by_count":0,"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":0.8988000154495239,"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":0.8988000154495239,"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":0.8981000185012817,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.8399999737739563,"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/question-answering","display_name":"Question answering","score":0.7923872470855713},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5758118629455566},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3398999571800232},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32218310236930847}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7923872470855713},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5758118629455566},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3398999571800232},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32218310236930847}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2410.23511","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.23511","pdf_url":"https://arxiv.org/pdf/2410.23511","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.23511","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.23511","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.23511","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.23511","pdf_url":"https://arxiv.org/pdf/2410.23511","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404346653.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Research":[0],"has":[1],"shown":[2],"the":[3,19,94,100,105,125,148,154],"effectiveness":[4],"of":[5,21,43,53],"reasoning":[6],"(e.g.,":[7,10],"Chain-of-Thought),":[8],"planning":[9],"SelfAsk),":[11],"and":[12,49,57,81,103,119],"retrieval":[13],"augmented":[14],"generation":[15,108],"strategies":[16],"to":[17,39,69,78,92,113,122,153],"improve":[18,79,141],"performance":[20,48,80,143],"Large":[22],"Language":[23],"Models":[24],"(LLMs)":[25],"on":[26,99,129],"various":[27],"tasks,":[28],"such":[29],"as":[30],"question":[31,102,133],"answering.":[32],"However,":[33],"using":[34],"a":[35,65,71],"single":[36],"fixed":[37],"strategy":[38,73,97],"answer":[40],"different":[41],"kinds":[42],"questions":[44],"is":[45],"suboptimal":[46],"in":[47,51,76,84],"inefficient":[50],"terms":[52],"generated":[54,126],"output":[55],"tokens":[56],"performed":[58],"retrievals.":[59],"In":[60],"our":[61],"work,":[62],"we":[63],"propose":[64],"novel":[66],"technique":[67],"DyPlan,":[68],"induce":[70],"dynamic":[72],"selection":[74],"process":[75,121],"LLMs,":[77],"reduce":[82],"costs":[83],"question-answering.":[85],"DyPlan":[86,112,139],"incorporates":[87],"an":[88,116],"initial":[89],"decision":[90],"step":[91],"select":[93],"most":[95],"suitable":[96],"conditioned":[98],"input":[101],"guides":[104],"LLM's":[106],"response":[107],"accordingly.":[109],"We":[110],"extend":[111],"DyPlan-verify,":[114],"adding":[115],"internal":[117],"verification":[118],"correction":[120],"further":[123],"enrich":[124],"answer.":[127],"Experiments":[128],"three":[130],"prominent":[131],"multi-hop":[132],"answering":[134],"(MHQA)":[135],"datasets":[136],"reveal":[137],"how":[138],"can":[140],"model":[142],"by":[144,150],"7-13%":[145],"while":[146],"reducing":[147],"cost":[149],"11-32%":[151],"relative":[152],"best":[155],"baseline":[156],"model.":[157]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}