{"id":"https://openalex.org/W4412888452","doi":"https://doi.org/10.18653/v1/2025.findings-acl.472","title":"HellaSwag-Pro: A Large-Scale Bilingual Benchmark for Evaluating the Robustness of LLMs in Commonsense Reasoning","display_name":"HellaSwag-Pro: A Large-Scale Bilingual Benchmark for Evaluating the Robustness of LLMs in Commonsense Reasoning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888452","doi":"https://doi.org/10.18653/v1/2025.findings-acl.472"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.472","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.472","pdf_url":"https://aclanthology.org/2025.findings-acl.472.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: ACL 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.472.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100603570","display_name":"Xiaoyuan Li","orcid":"https://orcid.org/0009-0001-7560-9414"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoyuan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104285550","display_name":"Moxin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moxin Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004626105","display_name":"Rui Men","orcid":"https://orcid.org/0000-0002-4429-3461"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Men","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013763116","display_name":"Yichang Zhang","orcid":"https://orcid.org/0000-0001-5388-6376"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yichang Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013954858","display_name":"Keqin Bao","orcid":"https://orcid.org/0009-0001-5910-0204"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keqin Bao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368524","display_name":"Wenjie Wang","orcid":"https://orcid.org/0000-0002-5199-1428"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjie Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051925942","display_name":"Fuli Feng","orcid":"https://orcid.org/0000-0002-5828-9842"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fuli Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062188134","display_name":"Dayiheng Liu","orcid":"https://orcid.org/0000-0002-8755-8941"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dayiheng Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100612233","display_name":"Junyang Lin","orcid":"https://orcid.org/0000-0001-9931-383X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junyang Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87766822,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"9038","last_page":"9072"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9757999777793884,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9757999777793884,"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/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.8366883993148804},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7620612382888794},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6179006695747375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5951123237609863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5254087448120117},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.46581578254699707},{"id":"https://openalex.org/keywords/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.4453851282596588},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34229475259780884},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.11565771698951721},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10759511590003967},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07801198959350586},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06486910581588745}],"concepts":[{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.8366883993148804},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7620612382888794},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6179006695747375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5951123237609863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5254087448120117},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.46581578254699707},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.4453851282596588},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34229475259780884},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.11565771698951721},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10759511590003967},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07801198959350586},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06486910581588745},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.472","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.472","pdf_url":"https://aclanthology.org/2025.findings-acl.472.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: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.472","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.472","pdf_url":"https://aclanthology.org/2025.findings-acl.472.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: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320325599","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888452.pdf","grobid_xml":"https://content.openalex.org/works/W4412888452.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3035583586","https://openalex.org/W4320165839","https://openalex.org/W2151799802","https://openalex.org/W2196562041","https://openalex.org/W4385488510","https://openalex.org/W2073302931","https://openalex.org/W3206107299","https://openalex.org/W3082691151","https://openalex.org/W4287633646","https://openalex.org/W4378501473"],"abstract_inverted_index":{"Large":[0],"language":[1,111],"models":[2,21],"(LLMs)":[3],"have":[4],"shown":[5],"remarkable":[6],"capabilities":[7],"in":[8,14,43,102,112,133],"commonsense":[9,24,44,103,134],"reasoning;":[10],"however,":[11],"some":[12],"variations":[13],"questions":[15],"can":[16],"trigger":[17],"incorrect":[18],"responses.Do":[19],"these":[20,96],"truly":[22],"understand":[23],"knowledge,":[25],"or":[26],"just":[27],"memorize":[28],"expression":[29],"patterns?To":[30],"investigate":[31],"this":[32,66,105],"question,":[33],"we":[34,68],"present":[35],"the":[36,110,114,131],"first":[37],"extensive":[38,88,125],"robustness":[39,106],"evaluation":[40,122],"of":[41,53,62],"LLMs":[42,97],"reasoning.We":[45],"introduce":[46],"HellaSwag-Pro,":[47],"a":[48,70,77,120],"large-scale":[49],"bilingual":[50],"benchmark":[51],"consisting":[52],"11,200":[54],"cases,":[55],"by":[56],"designing":[57],"and":[58],"compiling":[59],"seven":[60],"types":[61],"question":[63],"variants.To":[64],"construct":[65],"benchmark,":[67,123],"propose":[69],"two-stage":[71],"method":[72],"to":[73,130],"develop":[74],"Chinese":[75],"HellaSwag,":[76],"finely":[78],"annotated":[79],"dataset":[80],"comprising":[81],"12,000":[82],"instances":[83],"across":[84],"56":[85],"categories.We":[86],"conduct":[87],"experiments":[89,126],"on":[90,109],"41":[91],"representative":[92],"LLMs,":[93],"revealing":[94],"that":[95],"are":[98],"far":[99],"from":[100],"robust":[101],"reasoning.Furthermore,":[104],"varies":[107],"depending":[108],"which":[113],"LLM":[115],"is":[116],"tested.This":[117],"work":[118],"establishes":[119],"high-quality":[121],"with":[124],"offering":[127],"valuable":[128],"insights":[129],"community":[132],"reasoning":[135],"for":[136],"LLMs.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}