{"id":"https://openalex.org/W7221146835","doi":"https://doi.org/10.48550/arxiv.2610.11399","title":"Estimating Great Expectations Under Autoregressive Language Models with Potentials","display_name":"Estimating Great Expectations Under Autoregressive Language Models with Potentials","publication_year":2026,"publication_date":"2026-10-08","ids":{"openalex":"https://openalex.org/W7221146835","doi":"https://doi.org/10.48550/arxiv.2610.11399"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.11399","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.11399","pdf_url":"https://arxiv.org/pdf/2610.11399","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.11399","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020964192","display_name":"Francesco Ignazio Re","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Re, Francesco I.","raw_affiliation_strings":["ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158185349","display_name":"Shubhangi Ghosh","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ghosh, Shubhangi","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158009321","display_name":"Tim Vieira","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Vieira, Tim","raw_affiliation_strings":["ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061951606","display_name":"Ryan Cotterell","orcid":"https://orcid.org/0000-0003-4080-1833","observed_orcids":["https://orcid.org/0000-0003-4080-1833"]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Cotterell, Ryan","raw_affiliation_strings":["ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.5853999853134155,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.5853999853134155,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.21310000121593475,"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":0.09529999643564224,"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/autoregressive-language-models","display_name":"autoregressive language models","score":0.8830000162124634},{"id":"https://openalex.org/keywords/expectation-estimation","display_name":"expectation estimation","score":0.5619999766349792},{"id":"https://openalex.org/keywords/variance-reduction","display_name":"variance reduction","score":0.7540000081062317},{"id":"https://openalex.org/keywords/potential","display_name":"potential","score":0.8759999871253967},{"id":"https://openalex.org/keywords/entropy-estimation","display_name":"entropy estimation","score":0.8679999709129333},{"id":"https://openalex.org/keywords/watermark-detection","display_name":"watermark detection","score":0.9629999995231628},{"id":"https://openalex.org/keywords/rare-event-estimation","display_name":"rare event probability estimation","score":0.9909999966621399},{"id":"https://openalex.org/keywords/monte-carlo-estimation","display_name":"Monte Carlo estimation","score":0.6980000138282776},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"importance sampling","score":0.8930000066757202}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6672000288963318},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.613099992275238},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5562000274658203},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5379999876022339},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.5331000089645386},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4343999922275543},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C21430997","wikidata":"https://www.wikidata.org/wiki/Q5159279","display_name":"Conditional variance","level":4,"score":0.35510000586509705},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34599998593330383},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C186215838","wikidata":"https://www.wikidata.org/wiki/Q772232","display_name":"Conditional expectation","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3000999987125397},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C3018076075","wikidata":"https://www.wikidata.org/wiki/Q1826427","display_name":"Variance components","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2614000141620636},{"id":"https://openalex.org/C119043178","wikidata":"https://www.wikidata.org/wiki/Q320723","display_name":"Covariate","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.11399","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.11399","pdf_url":"https://arxiv.org/pdf/2610.11399","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.11399","doi":"https://doi.org/10.48550/arxiv.2610.11399","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.11399","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.11399","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.11399","pdf_url":"https://arxiv.org/pdf/2610.11399","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7221146835.pdf","grobid_xml":"https://content.openalex.org/works/W7221146835.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W201155865","https://openalex.org/W1191599655","https://openalex.org/W1821462560","https://openalex.org/W1995053220","https://openalex.org/W2024762727","https://openalex.org/W2044912718","https://openalex.org/W2130750514","https://openalex.org/W2736601468","https://openalex.org/W4292691288","https://openalex.org/W4385822366","https://openalex.org/W4399198340","https://openalex.org/W4404783468","https://openalex.org/W4414844329","https://openalex.org/W7128372175","https://openalex.org/W7156105003"],"related_works":["https://openalex.org/W7221861746","https://openalex.org/W4403579815","https://openalex.org/W7170044825","https://openalex.org/W7204534234","https://openalex.org/W4416047156","https://openalex.org/W7160536371","https://openalex.org/W2892183651","https://openalex.org/W3092500904","https://openalex.org/W1768488313","https://openalex.org/W203696055"],"abstract_inverted_index":{"Many":[0],"applications":[1,75],"of":[2,9,39,47,54,62],"language":[3],"models":[4],"require":[5],"estimating":[6],"the":[7,14,55],"expectation":[8],"a":[10,37,60],"test":[11,56],"functional":[12],"under":[13],"model.":[15],"Obtaining":[16],"precise":[17],"estimates":[18],"can":[19],"be":[20],"computationally":[21],"expensive.":[22],"We":[23,58],"show":[24],"how":[25],"to":[26,92],"improve":[27],"estimation":[28],"precision":[29],"by":[30,65],"exploiting":[31],"next-token":[32],"conditional":[33],"probabilities":[34],"available":[35],"as":[36],"by-product":[38],"sampling.":[40],"Our":[41],"approach":[42],"uses":[43],"potentials:":[44],"real-valued":[45],"functions":[46],"prefixes":[48],"that":[49],"induce":[50],"an":[51],"additive":[52],"decomposition":[53],"functional.":[57],"construct":[59],"family":[61],"estimators":[63,86],"parameterized":[64],"these":[66],"potentials":[67],"and":[68,81,95],"derive":[69],"conditions":[70],"for":[71],"variance":[72,89],"reduction.":[73],"Across":[74],"including":[76],"entropy":[77],"estimation,":[78,84],"watermark":[79],"detection,":[80],"rare-event":[82],"probability":[83],"our":[85],"achieve":[87],"substantial":[88],"reductions":[90],"relative":[91],"Monte":[93],"Carlo":[94],"importance":[96],"sampling":[97],"baselines":[98],"at":[99],"comparable":[100],"computational":[101],"cost.":[102]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-10T00:00:00"}