{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T01:13:55Z","timestamp":1783646035720,"version":"3.55.0"},"reference-count":23,"publisher":"Aerospace Medical Association","issue":"7","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:p>\n                    <jats:bold>INTRODUCTION:<\/jats:bold>\n                    Long-duration spaceflight exposes crews to isolated, confined, and extreme environments where chronic stress and limited real-time support heighten interpersonal tensions. Large language models (LLMs) could serve as onboard artificial intelligence teammates for de-escalation, but could also exacerbate tensions by endorsing hostility or exclusion. This study evaluates whether LLMs demonstrate prosocial conflict mediation behaviors vs. failure modes that could elevate interpersonal risk.\n                  <\/jats:p>\n                  <jats:p>\n                    <jats:bold>METHODS:<\/jats:bold>\n                    We tested four LLMs (GPT-5, Claude Sonnet 4, Grok 4, Gemini 2.5 Pro) using a Dartmouth PATH Program scenario where one crewmember criticizes an absent teammate and tries to recruit another against him. Models were evaluated across seven test batteries: adversarial framing, backstory manipulation, team role variations, aggressor identity variations, target identity variations, mental health sensitivity, and direct ethics questions. We scored 196 responses using a three-point rubric (defended excluded teammate, neutral, or endorsed exclusion).\n                  <\/jats:p>\n                  <jats:p>\n                    <jats:bold>RESULTS:<\/jats:bold>\n                    Claude Sonnet 4 achieved perfect scores (3.0). GPT-5 averaged 2.97. Gemini 2.5 Pro (2.81) showed vulnerability to narrative capture, shifting from defending the excluded crewmember to endorsing criticism when given unfavorable backstory. Grok 4 (2.85) exhibited significant failure under social proof pressure, explicitly endorsing exclusion. All models showed consistent prosocial responses regardless of demographic factors and correctly identified ethical issues when questioned directly.\n                  <\/jats:p>\n                  <jats:p>\n                    <jats:bold>DISCUSSION:<\/jats:bold>\n                    LLMs show promise as behavioral health teammates but have critical vulnerabilities. They can be manipulated into endorsing teammate exclusion through backstory reframing, peer pressure, or authority hierarchies, requiring safety protocols before deployment.\n                  <\/jats:p>\n                  <jats:p>\n                    <jats:bold>\n                      Dvorak C, Buckey JC Jr.\n                      <jats:italic>Large language models as behavioral health teammates in long-duration spaceflight<\/jats:italic>\n                      . Aerosp Med Hum Perform. 2026; 97(7):516\u2013523.\n                    <\/jats:bold>\n                  <\/jats:p>","DOI":"10.3357\/amhp.6892.2026","type":"journal-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T00:30:29Z","timestamp":1783643429000},"page":"516-523","source":"Crossref","is-referenced-by-count":0,"title":["Large Language Models as Behavioral Health Teammates in Long-Duration Spaceflight"],"prefix":"10.3357","volume":"97","author":[{"given":"Claire","family":"Dvorak","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jay C.","family":"Buckey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1911","reference":[{"issue":"9607","key":"B1","series-title":"Lancet.","first-page":"153","article-title":"Psychological effects of polar expeditions","volume":"371","author":"Palinkas LA","year":"2008","unstructured":"Palinkas LA, Suedfeld P. Psychological effects of polar expeditions. Lancet. 2008 Jan 12; 371(9607):153\u201363."},{"issue":"7","key":"B2","series-title":"Aviat Space Environ Med.","first-page":"617","article-title":"Interpersonal relations during simulated space missions","volume":"66","author":"Sandal GM","year":"1995","unstructured":"Sandal GM, Vaernes R, Ursin H. Interpersonal relations during simulated space missions. Aviat Space Environ Med. 1995 Jul; 66(7):617\u201324."},{"key":"B3","series-title":"Space Psychology and Psychiatry.","first-page":"35","author":"Kanas N","year":"2008","unstructured":"Kanas N, Manzey D. Space Psychology and Psychiatry. 2nd ed. Dordrecht (Netherlands): Springer; 2008:35\u20136., 98\u20139."},{"issue":"2","key":"B4","series-title":"Gravit Space Biol Bull.","first-page":"49","article-title":"Bold endeavors: behavioral lessons from polar and space exploration","volume":"13","author":"Stuster J.","year":"2000","unstructured":"Stuster J. Bold endeavors: behavioral lessons from polar and space exploration. Gravit Space Biol Bull. 2000 Jun; 13(2):49\u201357."},{"issue":"3","key":"B5","series-title":"PLoS One.","first-page":"e93298","article-title":"Psychological and behavioral changes during confinement in a 520-day simulated interplanetary mission to Mars","volume":"9","author":"Basner M","year":"2014","unstructured":"Basner M, Dinges DF, Mollicone DJ, Savelev I, Ecker AJ,  Psychological and behavioral changes during confinement in a 520-day simulated interplanetary mission to Mars. PLoS One. 2014 Mar 27; 9(3):e93298."},{"key":"B6","article-title":"Evidence report: risk of performance and behavioral health decrements due to inadequate cooperation, coordination, communication, and psychosocial adaptation within a team","author":"Landon LB.","year":"2022","unstructured":"Landon LB. Evidence report: risk of performance and behavioral health decrements due to inadequate cooperation, coordination, communication, and psychosocial adaptation within a team. Houston (TX): NASA Human Research Program; 2022."},{"issue":"4","key":"B7","series-title":"Am Psychol.","first-page":"563","article-title":"Teamwork and collaboration in long-duration space missions: going to extremes","volume":"73","author":"Landon LB","year":"2018","unstructured":"Landon LB, Slack KJ, Barrett JD. Teamwork and collaboration in long-duration space missions: going to extremes. Am Psychol. 2018 May-Jun; 73(4):563\u201375."},{"key":"B8","series-title":"Interact J Med Res.","first-page":"e58803","article-title":"Automated psychotherapy in a spaceflight environment: advantages, drawbacks, and unknowns","volume":"13","author":"Smith L.","year":"2024","unstructured":"Smith L. Automated psychotherapy in a spaceflight environment: advantages, drawbacks, and unknowns. Interact J Med Res. 2024 Oct 9; 13:e58803."},{"key":"B9","series-title":"Psychiatry Res.","first-page":"116583","article-title":"Assessing the accuracy and consistency of large language models in triaging social media posts for psychological distress","volume":"351","author":"Settanni M","year":"2025","unstructured":"Settanni M, Quilghini F, Toscano A, Marengo D. Assessing the accuracy and consistency of large language models in triaging social media posts for psychological distress. Psychiatry Res. 2025 Sept; 351:116583."},{"issue":"1","key":"B10","series-title":"NPJ Cardiovasc Health.","first-page":"48","article-title":"Fine-tuning LLMs in behavioral psychology for scalable health coaching","volume":"2","author":"Mantena S","year":"2025","unstructured":"Mantena S, Johnson A, Oppezzo M, Sch\u00fctz N, Tolas A,  Fine-tuning LLMs in behavioral psychology for scalable health coaching. NPJ Cardiovasc Health. 2025; 2(1):48."},{"issue":"1","key":"B11","series-title":"J Soc Issues.","first-page":"81","article-title":"Machines and mindlessness: social responses to computers","volume":"56","author":"Nass C","year":"2000","unstructured":"Nass C, Moon Y. Machines and mindlessness: social responses to computers. J Soc Issues. 2000 Spring; 56(1):81\u2013103."},{"issue":"2","key":"B12","series-title":"ACM Trans Comput-Hum Interact.","first-page":"293","article-title":"Establishing and maintaining long-term human-computer relationships","volume":"12","author":"Bickmore TW","year":"2005","unstructured":"Bickmore TW, Picard RW. Establishing and maintaining long-term human-computer relationships. ACM Trans Comput-Hum Interact. 2005 Jun; 12(2):293\u2013327."},{"key":"B13","article-title":"Training a helpful and harmless assistant with reinforcement learning from human feedback","author":"Bai Y","year":"2022","unstructured":"Bai Y, Jones A, Ndousse K, Askell A, Chen A,  Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv preprint arXiv:2204.058622022. [Accessed 28 May 2026]. Available from https:\/\/arxiv.org\/abs\/2204.05862."},{"key":"B14","article-title":"Towards understanding sycophancy in language models","author":"Sharma M","year":"2023","unstructured":"Sharma M, Tong M, Korbak T, Duvenaud D, Askell A,  Towards understanding sycophancy in language models. arXiv preprint arXiv:2310.135482023. [Accessed 28 May 2026]. Available from https:\/\/arxiv.org\/abs\/2310.13548."},{"key":"B15","article-title":"Holistic evaluation of language models","author":"Liang P","year":"2022","unstructured":"Liang P, Bommasani R, Lee T, Tsipras D, Soylu D,  Holistic evaluation of language models. arXiv preprint arXiv:2211.091102022. [Accessed 28 May 2026]. Available from https:\/\/arxiv.org\/abs\/2211.09110."},{"key":"B16","series-title":"NPJ Digit Med.","first-page":"43","article-title":"Methods in predictive techniques for mental health status on social media: a critical review","volume":"3","author":"Chancellor S","year":"2020","unstructured":"Chancellor S, De Choudhury M. Methods in predictive techniques for mental health status on social media: a critical review. NPJ Digit Med. 2020 Mar 24; 3:43."},{"key":"B17","series-title":"Space Physiology.","first-page":"34","author":"Buckey JC Jr","year":"2006","unstructured":"Buckey JC Jr. Space Physiology. New York (NY): Oxford University Press; 2006:34\u201345."},{"issue":"11","key":"B18","series-title":"Aerosp Med Hum Perform.","first-page":"912","article-title":"Autonomous, computer-based behavioral health countermeasure evaluation at HI-SEAS Mars analog","volume":"87","author":"Anderson AP","year":"2016","unstructured":"Anderson AP, Fellows AM, Binsted KA, Hegel MT, Buckey JC. Autonomous, computer-based behavioral health countermeasure evaluation at HI-SEAS Mars analog. Aerosp Med Hum Perform. 2016; 87(11):912\u201320."},{"issue":"6","key":"B19","series-title":"Aviat Space Environ Med.","first-page":"556","article-title":"Subject\u2019s perceptions of the crew interaction dynamics under prolonged isolation","volume":"69","author":"Gushin VI","year":"1998","unstructured":"Gushin VI, Efimov VA, Smirnova TM, Vinokhodova AG, Kanas N. Subject\u2019s perceptions of the crew interaction dynamics under prolonged isolation. Aviat Space Environ Med. 1998 Jun; 69(6):556\u201361."},{"key":"B20","series-title":"Groupthink: Psychological Studies of Policy Decisions and Fiascoes.","first-page":"174","author":"Janis IL.","year":"1982","unstructured":"Janis IL. Groupthink: Psychological Studies of Policy Decisions and Fiascoes. 2nd ed. Boston (MA): Houghton Mifflin; 1982:174\u201397."},{"key":"B21","series-title":"Culture at Work in Aviation and Medicine.","first-page":"53","author":"Helmreich RL","year":"1998","unstructured":"Helmreich RL, Merritt AC. Culture at Work in Aviation and Medicine. Aldershot (UK): Ashgate; 1998:53\u2013106."},{"key":"B22","series-title":"NPJ Ment Health Res.","first-page":"12","article-title":"Large language models could change the future of behavioral healthcare: a proposal for responsible development and evaluation","volume":"3","author":"Stade EC","year":"2024","unstructured":"Stade EC, Stirman SW, Ungar LH, Boland CL, Schwartz HA,  Large language models could change the future of behavioral healthcare: a proposal for responsible development and evaluation. NPJ Ment Health Res. 2024 Apr 2; 3(1):12."},{"issue":"3","key":"B23","series-title":"J Exp Soc Psychol.","first-page":"581","article-title":"Dual-process morality and the personal\/impersonal distinction: a reply to McGuire, Langdon, Coltheart, and Mackenzie","volume":"45","author":"Greene JD.","year":"2009","unstructured":"Greene JD. Dual-process morality and the personal\/impersonal distinction: a reply to McGuire, Langdon, Coltheart, and Mackenzie. J Exp Soc Psychol. 2009 May; 45(3):581\u20134."}],"container-title":["Aerospace Medicine and Human Performance"],"original-title":[],"link":[{"URL":"https:\/\/asma.kglmeridian.com\/view\/journals\/amhp\/97\/7\/article-p516.xml","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/asma.kglmeridian.com\/downloadpdf\/journals\/amhp\/97\/7\/article-p516.xml","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/asma.kglmeridian.com\/downloadpdf\/journals\/amhp\/97\/7\/article-p516.xml","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T00:30:41Z","timestamp":1783643441000},"score":1,"resource":{"primary":{"URL":"https:\/\/asma.kglmeridian.com\/view\/journals\/amhp\/97\/7\/article-p516.xml"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":23,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.3357\/amhp.6892.2026","relation":{},"ISSN":["2375-6314","2375-6322"],"issn-type":[{"value":"2375-6314","type":"print"},{"value":"2375-6322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}