{"id":"https://openalex.org/W4416940387","doi":"https://doi.org/10.48550/arxiv.2511.21714","title":"GPS: General Per-Sample Prompter","display_name":"GPS: General Per-Sample Prompter","publication_year":2025,"publication_date":"2025-11-18","ids":{"openalex":"https://openalex.org/W4416940387","doi":"https://doi.org/10.48550/arxiv.2511.21714"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2511.21714","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.21714","pdf_url":"https://arxiv.org/pdf/2511.21714","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"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/2511.21714","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120679961","display_name":"Pawel Batorski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Batorski, Pawel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5070897658","display_name":"Paul Swoboda","orcid":"https://orcid.org/0000-0003-4065-8758"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Swoboda, Paul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T13629","display_name":"Text Readability and Simplification","score":0.367000013589859,"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/T13629","display_name":"Text Readability and Simplification","score":0.367000013589859,"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":0.28630000352859497,"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":0.16140000522136688,"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/task","display_name":"Task (project management)","score":0.5095999836921692},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4763000011444092},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.4668000042438507},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.45329999923706055},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.38749998807907104},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3783999979496002},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.35589998960494995},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3255000114440918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7670000195503235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5891000032424927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5450999736785889},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5095999836921692},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4763000011444092},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.4668000042438507},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.45329999923706055},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3783999979496002},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2759000062942505},{"id":"https://openalex.org/C60229501","wikidata":"https://www.wikidata.org/wiki/Q18822","display_name":"Global Positioning System","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2533000111579895},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2511.21714","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.21714","pdf_url":"https://arxiv.org/pdf/2511.21714","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.21714","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.21714","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.21714","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.21714","pdf_url":"https://arxiv.org/pdf/2511.21714","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"LLMs":[0],"are":[1],"sensitive":[2],"to":[3,49,74,79,130,140,178,213],"prompting,":[4,183],"with":[5,113],"task":[6],"performance":[7,105],"often":[8],"hinging":[9],"on":[10,55,116,155,161,166,171,187],"subtle,":[11],"sometimes":[12],"imperceptible":[13],"variations":[14],"in":[15,176],"phrasing.":[16],"As":[17],"a":[18,66,97,117,124,195,214],"result,":[19],"crafting":[20],"effective":[21,198],"prompts":[22,206],"manually":[23],"remains":[24],"challenging":[25],"and":[26,122,163,197,210],"time-consuming.":[27],"Recent":[28],"automatic":[29,201],"prompting":[30,89],"methods":[31],"mitigate":[32],"this":[33],"difficulty":[34],"but":[35],"face":[36],"three":[37],"key":[38],"limitations:":[39],"(i)":[40],"for":[41,100,127,200],"each":[42,101],"new":[43],"task,":[44],"they":[45,53],"require":[46],"large":[47],"datasets":[48],"train":[50],"good":[51],"prompts;(ii)":[52],"rely":[54],"costly":[56],"optimization":[57,209],"loops":[58],"that":[59,70],"may":[60],"take":[61],"hours;":[62],"(iii)they":[63],"typically":[64],"produce":[65],"single":[67],"task-level":[68],"prompt":[69,99],"does":[71],"not":[72,169],"adapt":[73],"the":[75,85,179,192],"individual":[76],"input":[77],"problem":[78],"be":[80],"solved.":[81],"We":[82],"propose":[83],"GPS,":[84],"first":[86],"general-purpose,":[87],"per-sample":[88,131],"method.":[90],"Without":[91],"any":[92,172],"task-specific":[93,215],"tuning,":[94],"GPS":[95,144],"generates":[96],"tailored":[98],"unseen":[102],"input,":[103],"improving":[104],"across":[106],"diverse":[107],"tasks.":[108],"The":[109],"prompter":[110],"is":[111,220],"trained":[112],"reinforcement":[114],"learning":[115],"suite":[118],"of":[119,173,194],"training":[120,170,216],"tasks":[121],"includes":[123],"novel":[125,196],"regularization":[126],"effectively":[128],"adapting":[129],"prompting.":[132],"Finally,":[133],"we":[134,148,184],"employ":[135],"Minimum":[136],"Bayes":[137],"Risk":[138],"decoding":[139],"stabilize":[141],"inference.":[142],"Empirically,":[143],"demonstrates":[145],"competitive":[146],"performance:":[147],"attain":[149],"second":[150],"best":[151,159],"results":[152,160,165],"among":[153],"baselines":[154],"text":[156],"simplification,":[157],"third":[158],"summarization":[162],"on-par":[164],"classification,":[167],"while":[168],"these":[174],"tasks,":[175],"contrast":[177],"baselines.":[180],"For":[181],"in-domain":[182],"obtain":[185],"sota":[186],"GSM8K.":[188],"Our":[189,218],"work":[190],"shows":[191],"potential":[193],"paradigm":[199],"prompting:":[202],"generating":[203],"adaptive,":[204],"input-specific":[205],"without":[207,211],"extensive":[208],"access":[212],"set.":[217],"code":[219],"available":[221],"at":[222],"https://github.com/Batorskq/GPS.":[223]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-03T00:00:00"}