{"id":"https://openalex.org/W4391093147","doi":"https://doi.org/10.1109/bigdata59044.2023.10386712","title":"Mitigating Annotation Artifacts in Physical Commonsense Reasoning Benchmark","display_name":"Mitigating Annotation Artifacts in Physical Commonsense Reasoning Benchmark","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391093147","doi":"https://doi.org/10.1109/bigdata59044.2023.10386712"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata59044.2023.10386712","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055447626","display_name":"Wing-Lam Mok","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wing-Lam Mok","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,South Korea","Department of Artificial Intelligence, Korea University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,South Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100619133","display_name":"Sungho Kim","orcid":"https://orcid.org/0000-0002-3786-6807"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"SungHo Kim","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,South Korea","Department of Artificial Intelligence, Korea University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,South Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19171589,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6236","last_page":"6238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9991000294685364,"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":0.9950000047683716,"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/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.955819845199585},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7802430391311646},{"id":"https://openalex.org/keywords/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.7656069993972778},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7568208575248718},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6659348011016846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5722274780273438},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4211497902870178},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.41609928011894226},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3850085735321045},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3681246042251587},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.15977022051811218}],"concepts":[{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.955819845199585},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7802430391311646},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.7656069993972778},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7568208575248718},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6659348011016846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5722274780273438},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4211497902870178},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.41609928011894226},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3850085735321045},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3681246042251587},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.15977022051811218},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata59044.2023.10386712","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2251919380","https://openalex.org/W2896457183","https://openalex.org/W2952984539","https://openalex.org/W2962736243","https://openalex.org/W2962843521","https://openalex.org/W2963115613","https://openalex.org/W2965373594","https://openalex.org/W2970442950","https://openalex.org/W2980282514","https://openalex.org/W2996908057","https://openalex.org/W2997616454","https://openalex.org/W2998617917","https://openalex.org/W3175287561","https://openalex.org/W3213868621","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6768817161"],"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":{"To":[0],"achieve":[1],"human-like":[2],"AI,":[3],"physical":[4,19,36,106],"commonsense":[5,20,107,112],"reasoning":[6,21,113],"plays":[7],"a":[8,83],"pivotal":[9],"role":[10],"for":[11,70],"machines":[12],"to":[13,27,63,88,94],"understand":[14,34],"the":[15,35,39,71,75,90,99,110,116],"real":[16,111],"world.":[17],"Thereby,":[18],"benchmarks":[22,67],"[1]\u2013[3]":[23],"have":[24,47,57],"been":[25],"developed":[26],"evaluate":[28],"how":[29],"well":[30],"language":[31,44],"models":[32,45,61],"can":[33],"characteristics":[37],"and":[38],"corresponding":[40],"utilization.":[41],"While":[42],"pre-trained":[43],"(PLMs)":[46],"shown":[48],"remarkable":[49],"performances":[50],"on":[51,102],"such":[52],"benchmarks,":[53],"recent":[54],"studies":[55],"[4]":[56],"discovered":[58],"that":[59,92],"these":[60],"tend":[62],"exploit":[64],"artifacts":[65,91],"in":[66,105],"as":[68],"shortcuts":[69],"over-estimated":[72],"results,":[73],"overpassing":[74],"actual":[76],"reasoning.":[77],"In":[78],"this":[79],"paper,":[80],"we":[81],"propose":[82],"novel":[84],"crowdsouring":[85],"MAA":[86],"framework":[87],"mitigate":[89],"leads":[93],"shortcut":[95],"effect":[96],"revealed":[97],"by":[98],"stress":[100],"test":[101],"partial":[103],"input":[104],"reasoning,":[108],"disclosing":[109],"ability":[114],"of":[115],"PLMs.":[117]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}