{"id":"https://openalex.org/W4416034460","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1353","title":"OptiSeq: Ordering Examples On-The-Fly for In-Context Learning","display_name":"OptiSeq: Ordering Examples On-The-Fly for In-Context Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034460","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1353"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1353","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1353","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1353.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1353.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070636839","display_name":"Rahul Atul Bhope","orcid":"https://orcid.org/0000-0002-4155-8161"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rahul Atul Bhope","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047726169","display_name":"Praveen Venkateswaran","orcid":"https://orcid.org/0000-0003-0042-4164"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Praveen Venkateswaran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086724836","display_name":"K. R. Jayaram","orcid":"https://orcid.org/0000-0001-5382-276X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"K. R. Jayaram","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047019446","display_name":"Vatche Isahagian","orcid":"https://orcid.org/0000-0002-9573-9291"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vatche Isahagian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055833498","display_name":"Vinod Muthusamy","orcid":"https://orcid.org/0000-0003-0614-2563"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vinod Muthusamy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5060176636","display_name":"Nalini Venkatasubramanian","orcid":"https://orcid.org/0000-0001-7011-2268"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nalini Venkatasubramanian","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":3.346,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93494707,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"24864","last_page":"24887"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.20600000023841858,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.20600000023841858,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.19539999961853027,"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"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.14569999277591705,"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/feature","display_name":"Feature (linguistics)","score":0.2939000129699707},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.2535000145435333},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.24950000643730164},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.24570000171661377},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.24240000545978546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5447999835014343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4068000018596649},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.250900000333786},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.24950000643730164},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24809999763965607},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.24570000171661377},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.24240000545978546},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.23829999566078186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1353","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1353","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1353.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"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1353","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1353","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1353.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":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034460.pdf","grobid_xml":"https://content.openalex.org/works/W4416034460.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Developers":[0],"using":[1],"LLMs":[2],"and":[3,30,96,110,120],"LLM-based":[4],"agents":[5],"in":[6,25,36,43],"their":[7,54],"applications":[8],"have":[9],"provided":[10],"plenty":[11],"of":[12,32,49,84,93,108],"anecdotal":[13],"evidence":[14],"that":[15,24,74,104,112,123],"in-contextlearning":[16],"(ICL)":[17],"is":[18],"fragile.In":[19],"this":[20],"paper,":[21],"we":[22,65],"show":[23],"addition":[26],"to":[27,87],"the":[28,34,38,44,47,50,77,90,98],"quantity":[29],"quality":[31],"examples,":[33],"order":[35],"which":[37],"incontext":[39],"examples":[40],"are":[41],"listed":[42],"prompt":[45],"affects":[46],"output":[48],"LLM":[51],"and,":[52],"consequently,":[53],"performance.While":[55],"prior":[56],"work":[57],"has":[58],"explored":[59],"improving":[60],"ICL":[61],"through":[62],"datasetdependent":[63],"techniques,":[64],"introduce":[66],"OptiSeq,":[67],"a":[68],"purely":[69],"inference-time,":[70],"dataset-free":[71],"optimization":[72],"method":[73],"efficiently":[75],"determines":[76],"best":[78,99],"example":[79],"order.OptiSeq":[80],"leverages":[81],"log":[82],"probabilities":[83],"LLM-generated":[85],"outputs":[86],"systematically":[88],"prune":[89],"search":[91],"space":[92],"possible":[94],"orderings":[95,103],"recommend":[97],"order(s)":[100],"by":[101,127],"distinguishing":[102],"yield":[105],"high":[106],"levels":[107],"accuracy":[109,126],"those":[111],"underperform.Extensive":[113],"empirical":[114],"evaluation":[115],"on":[116],"multiple":[117,133],"LLMs,":[118],"datasets,":[119],"prompts":[121],"demonstrates":[122],"Op-tiSeq":[124],"improves":[125],"5.5":[128],"-10.5":[129],"percentage":[130],"points":[131],"across":[132],"tasks.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}