{"id":"https://openalex.org/W4415428757","doi":"https://doi.org/10.3233/faia250904","title":"RESPONSE: Benchmarking the Ability of Language Models to Undertake Commonsense Reasoning in Crisis Situation","display_name":"RESPONSE: Benchmarking the Ability of Language Models to Undertake Commonsense Reasoning in Crisis Situation","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428757","doi":"https://doi.org/10.3233/faia250904"},"language":"en","primary_location":{"id":"doi:10.3233/faia250904","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250904","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia250904","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053176793","display_name":"A\u00efssatou Diallo","orcid":"https://orcid.org/0000-0003-1556-2391"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Aissatou Diallo","raw_affiliation_strings":["Department of Computer Science, University College London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University College London, United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059707016","display_name":"Antonis Bikakis","orcid":"https://orcid.org/0000-0003-4162-1818"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Antonis Bikakis","raw_affiliation_strings":["Department of Information Studies, University College London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Department of Information Studies, University College London, United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071580635","display_name":"Luke Dickens","orcid":"https://orcid.org/0000-0003-2521-4649"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Luke Dickens","raw_affiliation_strings":["Department of Information Studies, University College London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Department of Information Studies, University College London, United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019854432","display_name":"Anthony Hunter","orcid":"https://orcid.org/0000-0001-5602-7446"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anthony Hunter","raw_affiliation_strings":["Department of Computer Science, University College London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University College London, United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112134412","display_name":"Rob Miller","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rob Miller","raw_affiliation_strings":["Department of Information Studies, University College London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Department of Information Studies, University College London, United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5053176793"],"corresponding_institution_ids":["https://openalex.org/I45129253"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.49818522,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.8726999759674072,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.8726999759674072,"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/T14236","display_name":"Educational Tools and Methods","score":0.8295000195503235,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8217999935150146,"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":0.8562999963760376},{"id":"https://openalex.org/keywords/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.7366999983787537},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6136999726295471},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5713000297546387},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.49869999289512634},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4544999897480011},{"id":"https://openalex.org/keywords/qualitative-reasoning","display_name":"Qualitative reasoning","score":0.41110000014305115},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.35179999470710754}],"concepts":[{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.8562999963760376},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.7366999983787537},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6559000015258789},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6136999726295471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5759000182151794},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5713000297546387},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.49869999289512634},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4544999897480011},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.41110000014305115},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3617999851703644},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.3382999897003174},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.33180001378059387},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2912999987602234},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.2824999988079071},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2653000056743622},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.26010000705718994}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/faia250904","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250904","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10213506","is_oa":false,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10213506/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"In: Lynce, In\u00eas and Murano, Nello and Vallati, Mauro and Villata, Serena and Chesani, Federico and Milano, Michela and Omicini, Andrea and Dastani, Mehdi, (eds.) Proceedings of the 28th European Conference on Artificial Intelligence (ECAI 2025).  (pp. pp. 967-974).  ECAI: Bologna, Italy. (2025)","raw_type":"Proceedings paper"}],"best_oa_location":{"id":"doi:10.3233/faia250904","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250904","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"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":{"Commonsense":[0],"reasoning":[1,30,42,76,145],"is":[2],"a":[3,59,97],"key":[4],"aspect":[5],"of":[6,28,34,40,69],"human":[7,35,108,115],"intelligence.":[8],"If":[9],"we":[10,20,56,110],"are":[11,47],"to":[12,22,72],"develop":[13],"robust":[14],"and":[15,26,93,107],"deep":[16],"intelligent":[17],"systems,":[18],"then":[19],"need":[21],"understand":[23],"the":[24,32],"diversity":[25],"complexity":[27],"commonsense":[29,41,75,144],"across":[31,80],"gamut":[33],"activities.":[36],"An":[37],"interesting":[38],"class":[39],"problems":[43],"arises":[44],"when":[45],"people":[46],"faced":[48],"with":[49,96],"natural":[50],"disasters.":[51],"To":[52],"investigate":[53],"this":[54],"topic,":[55],"present":[57],"RESPONSE,":[58],"human-curated":[60],"dataset":[61,85],"containing":[62],"1789":[63],"annotated":[64],"instances":[65],"featuring":[66],"6037":[67],"sets":[68],"questions":[70],"designed":[71],"assess":[73],"LLMs\u2019":[74,141],"in":[77,140,146],"disaster":[78],"situations":[79],"different":[81],"time":[82],"frames.":[83],"The":[84],"includes":[86],"problem":[87],"descriptions,":[88],"missing":[89],"resources,":[90],"time-sensitive":[91],"solutions,":[92],"their":[94],"justifications,":[95],"subset":[98],"validated":[99],"by":[100],"environmental":[101],"engineers.":[102],"Through":[103],"both":[104],"automatic":[105],"metrics":[106],"evaluation,":[109],"compare":[111],"LLM-generated":[112],"recommendations":[113],"against":[114],"responses.":[116],"Our":[117],"findings":[118],"show":[119],"that":[120],"even":[121],"state-of-the-art":[122],"models":[123],"like":[124],"GPT-4":[125],"achieve":[126],"only":[127],"37%":[128],"human-evaluated":[129],"correctness":[130],"for":[131,138,143],"immediate":[132],"response":[133],"actions,":[134],"highlighting":[135],"significant":[136],"room":[137],"improvement":[139],"ability":[142],"crises.":[147]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}