{"id":"https://openalex.org/W4403754206","doi":"https://doi.org/10.48550/arxiv.2407.11387","title":"A Framework for Evaluating Appropriateness, Trustworthiness, and Safety in Mental Wellness AI Chatbots","display_name":"A Framework for Evaluating Appropriateness, Trustworthiness, and Safety in Mental Wellness AI Chatbots","publication_year":2024,"publication_date":"2024-07-16","ids":{"openalex":"https://openalex.org/W4403754206","doi":"https://doi.org/10.48550/arxiv.2407.11387"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2407.11387","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.11387","pdf_url":"https://arxiv.org/pdf/2407.11387","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.11387","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074176434","display_name":"Lucia Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Lucia","raw_affiliation_strings":["Psyfy Inc. , United States ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Psyfy Inc. , United States ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049365731","display_name":"David A. Preece","orcid":"https://orcid.org/0000-0003-1060-2024","observed_orcids":["https://orcid.org/0000-0003-1060-2024","https://orcid.org/0009-0003-6816-452X","https://orcid.org/0000-0002-3182-1640"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Preece, David A.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001962007","display_name":"Pilleriin Sikka","orcid":"https://orcid.org/0000-0002-1926-6138","observed_orcids":["https://orcid.org/0000-0002-1926-6138"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sikka, Pilleriin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051095866","display_name":"James J. Gross","orcid":"https://orcid.org/0000-0003-3624-3090","observed_orcids":["https://orcid.org/0000-0003-3624-3090","https://orcid.org/0000-0001-6682-6559"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gross, James J.","raw_affiliation_strings":["Stanford University , Department of Psychology , United States ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University , Department of Psychology , United States ,","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114403012","display_name":"Ben Krause","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Krause, Ben","raw_affiliation_strings":["Psyfy Inc. , United States ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Psyfy Inc. , United States ,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"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/T11519","display_name":"Digital Mental Health Interventions","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/3202","display_name":"Applied Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11519","display_name":"Digital Mental Health Interventions","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/3202","display_name":"Applied Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.0010999999940395355,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.0010999999940395355,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7480000257492065},{"id":"https://openalex.org/keywords/transdiagnostic-cognitive-behavioral-therapy","display_name":"transdiagnostic cognitive behavioral therapy","score":0.8700000047683716},{"id":"https://openalex.org/keywords/chatbot-safety","display_name":"chatbot safety","score":0.765999972820282},{"id":"https://openalex.org/keywords/hallucinations","display_name":"hallucinations","score":0.6660000085830688},{"id":"https://openalex.org/keywords/user-engagement","display_name":"user engagement","score":0.8240000009536743}],"concepts":[{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.5920572876930237},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4939501881599426},{"id":"https://openalex.org/C134362201","wikidata":"https://www.wikidata.org/wiki/Q317309","display_name":"Mental health","level":2,"score":0.4557393193244934},{"id":"https://openalex.org/C75630572","wikidata":"https://www.wikidata.org/wiki/Q538904","display_name":"Applied psychology","level":1,"score":0.3620649576187134},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3548929691314697},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.3208720088005066},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.22105267643928528},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.16698694229125977}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2407.11387","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.11387","pdf_url":"https://arxiv.org/pdf/2407.11387","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2407.11387","doi":"https://doi.org/10.48550/arxiv.2407.11387","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.11387","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:2407.11387","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.11387","pdf_url":"https://arxiv.org/pdf/2407.11387","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.9476000070571899,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403754206.pdf","grobid_xml":"https://content.openalex.org/works/W4403754206.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4402385952","https://openalex.org/W7221339156","https://openalex.org/W7161109932","https://openalex.org/W7106686009","https://openalex.org/W7139932326","https://openalex.org/W7222656346","https://openalex.org/W7125774231","https://openalex.org/W7156598068","https://openalex.org/W4392934644","https://openalex.org/W7123344483"],"abstract_inverted_index":{"Large":[0],"language":[1],"model":[2],"(LLM)":[3],"chatbots":[4,97,101,118,130],"are":[5],"susceptible":[6],"to":[7,22,66,133,146,174],"biases":[8],"and":[9,51,108,115,138,167,178,181],"hallucinations,":[10],"but":[11],"current":[12],"evaluations":[13],"of":[14,53,83,86,163],"mental":[15,54],"wellness":[16,55],"technologies":[17],"lack":[18],"comprehensive":[19],"case":[20],"studies":[21],"evaluate":[23],"their":[24],"practical":[25,161],"applications.":[26],"Here,":[27],"we":[28],"address":[29],"this":[30],"gap":[31],"by":[32],"introducing":[33],"the":[34,48,75,99,116,164],"MHealth-EVAL":[35,76,165],"framework,":[36],"a":[37,61,80,160],"new":[38,62],"role-play":[39],"based":[40],"interactive":[41],"evaluation":[42],"method":[43],"designed":[44],"specifically":[45],"for":[46],"evaluating":[47],"appropriateness,":[49],"trustworthiness,":[50],"safety":[52],"chatbots.":[56,91],"We":[57,73],"also":[58],"introduce":[59],"Psyfy,":[60],"chatbot":[63],"leveraging":[64],"LLMs":[65,173],"facilitate":[67],"transdiagnostic":[68],"Cognitive":[69],"Behavioral":[70],"Therapy":[71],"(CBT).":[72],"demonstrate":[74],"framework's":[77],"utility":[78,170],"through":[79],"comparative":[81],"study":[82,158],"two":[84],"versions":[85],"Psyfy":[87,96,114,129],"against":[88],"standard":[89],"baseline":[90,100,117],"Our":[92,157],"results":[93],"showed":[94],"that":[95],"outperformed":[98],"in":[102,153,171],"delivering":[103],"appropriate":[104,182],"responses,":[105,142],"engaging":[106],"users,":[107],"avoiding":[109],"untrustworthy":[110],"responses.":[111],"However,":[112],"both":[113],"exhibited":[119],"some":[120],"limitations,":[121],"such":[122],"as":[123],"providing":[124],"predominantly":[125],"US-centric":[126],"resources.":[127],"While":[128],"were":[131],"able":[132],"identify":[134],"most":[135],"unsafe":[136,141],"situations":[137],"avoid":[139],"giving":[140],"they":[143],"sometimes":[144],"struggled":[145],"recognize":[147],"subtle":[148],"harmful":[149],"intentions":[150],"when":[151],"prompted":[152],"role":[154],"play":[155],"scenarios.":[156],"demonstrates":[159],"application":[162],"framework":[166],"showcases":[168],"Psyfy's":[169],"harnessing":[172],"enhance":[175],"user":[176],"engagement":[177],"provide":[179],"flexible":[180],"responses":[183],"aligned":[184],"with":[185],"an":[186],"evidence-based":[187],"CBT":[188],"approach.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2024-10-26T00:00:00"}
