{"id":"https://openalex.org/W7138385664","doi":"https://doi.org/10.1609/aaai.v40i21.38812","title":"Do Large Language Models Reason About Uncertainty Like Humans? A Benchmark on Hurricane Forecast Visualization Comprehension","display_name":"Do Large Language Models Reason About Uncertainty Like Humans? A Benchmark on Hurricane Forecast Visualization Comprehension","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138385664","doi":"https://doi.org/10.1609/aaai.v40i21.38812"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i21.38812","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i21.38812","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38812/42774","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38812/42774","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129738651","display_name":"Le Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Le Liu","raw_affiliation_strings":["Northwestern Polytechnical University"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129678938","display_name":"Yuhao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Wang","raw_affiliation_strings":["Northwestern Polytechnical University"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073118816","display_name":"Biao Shen","orcid":"https://orcid.org/0000-0002-5027-6158"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohan Shen","raw_affiliation_strings":["Northwestern Polytechnical University"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129685693","display_name":"Wei Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Zeng","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou)"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129742499","display_name":"Shizhou Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shizhou Zhang","raw_affiliation_strings":["Northwestern Polytechnical University"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129735984","display_name":"Di Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Di Xu","raw_affiliation_strings":["Huawei"],"affiliations":[{"raw_affiliation_string":"Huawei","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129716700","display_name":"Peng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Wang","raw_affiliation_strings":["Northwestern Polytechnical University"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5129738651"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74627976,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"21","first_page":"17571","last_page":"17579"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2824000120162964,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2824000120162964,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.16990000009536743,"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/T10799","display_name":"Data Visualization and Analytics","score":0.14409999549388885,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.7559000253677368},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.6924999952316284},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.6126000285148621},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.5633000135421753},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43939998745918274},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.4278999865055084},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.3944999873638153},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.39079999923706055}],"concepts":[{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.7559000253677368},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6924999952316284},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.6126000285148621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5715000033378601},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.5633000135421753},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43939998745918274},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.43220001459121704},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.4278999865055084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42730000615119934},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.3944999873638153},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.39079999923706055},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.3199999928474426},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.2818000018596649},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27799999713897705},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2718999981880188},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.26420000195503235},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C185578843","wikidata":"https://www.wikidata.org/wiki/Q10609775","display_name":"Information visualization","level":3,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i21.38812","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i21.38812","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38812/42774","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i21.38812","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i21.38812","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38812/42774","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4102078676223755}],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6462983346","display_name":null,"funder_award_id":"62472357","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138385664.pdf","grobid_xml":"https://content.openalex.org/works/W7138385664.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Uncertainty":[0],"visualizations,":[1],"such":[2],"as":[3],"hurricane":[4,76,91],"cones":[5],"and":[6,35,49,55,72,93,101,108,123,144,154,159],"ensemble":[7],"tracks,":[8],"are":[9,15,160],"essential":[10],"for":[11],"risk":[12],"communication":[13],"but":[14,166],"often":[16],"misinterpreted,":[17],"leading":[18],"to":[19,42,53],"harmful":[20],"decisions.":[21],"As":[22],"AI":[23],"assistants":[24],"like":[25],"large":[26],"language":[27],"models":[28],"(LLMs)":[29],"increasingly":[30],"support":[31],"understanding":[32,156],"of":[33,46,59,157],"graphics":[34],"decision-making,":[36],"they":[37],"offer":[38,176],"a":[39,50,151],"promising":[40],"pathway":[41],"enhance":[43],"the":[44,57,64],"interpretation":[45,58],"complex":[47],"visualizations":[48,107],"new":[51],"opportunity":[52],"examine":[54],"improve":[56],"uncertainty.":[60],"We":[61,137],"introduce":[62],"UnReason,":[63],"first":[65],"benchmark":[66],"that":[67,148],"systematically":[68],"compares":[69],"how":[70],"humans":[71],"LLMs":[73,98,102,149],"reason":[74],"about":[75],"forecast":[77],"uncertainty":[78,125,135],"visualizations.":[79],"UnReason":[80],"spans":[81],"two":[82],"escalating":[83],"phases,":[84],"seven":[85],"representative":[86],"visualization":[87],"formats,":[88],"six":[89],"real":[90],"cases,":[92],"three":[94],"agent":[95],"types":[96],"(humans,":[97],"with":[99,182],"context,":[100],"without":[103],"context),":[104],"including":[105],"880":[106],"117,600":[109],"structured":[110],"question\u2013answer":[111],"pairs":[112],"under":[113,131],"matched":[114],"evaluation":[115],"conditions.":[116],"Phase":[117,127],"1":[118],"evaluates":[119],"reasoning":[120,130,142,188],"across":[121],"implicit":[122],"explicit":[124],"encodings;":[126],"2":[128],"examines":[129],"single-":[132],"versus":[133],"multi-dimensional":[134],"representations.":[136],"thoroughly":[138],"assess":[139],"damage":[140],"estimation,":[141],"strategies,":[143],"comprehension":[145],"patterns,":[146],"revealing":[147],"have":[150],"stronger":[152],"semantic":[153],"conceptual":[155],"uncertainty,":[158],"less":[161],"misled":[162],"by":[163],"visual":[164,187],"variability,":[165],"still":[167],"replicate":[168],"key":[169],"human":[170,183],"biases":[171],"during":[172],"decision-making.":[173],"Our":[174],"findings":[175],"insights":[177],"into":[178],"aligning":[179],"LLM":[180],"behavior":[181],"cognition":[184],"in":[185],"uncertainty-rich":[186],"tasks.":[189]},"counts_by_year":[],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2026-03-18T00:00:00"}
