{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T07:47:13Z","timestamp":1782546433217,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":116,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T00:00:00Z","timestamp":1779148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,5,19]]},"DOI":"10.1145\/3801487.3802805","type":"proceedings-article","created":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T07:05:47Z","timestamp":1782543947000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Architecturally Aligned Trustworthy AI: Substrate and System Design Strategies for Next Generation AI"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8016-5563","authenticated-orcid":false,"given":"Eren","family":"Kurshan","sequence":"first","affiliation":[{"name":"Princeton University, New Jersey, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,27]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"H. Ahlenius et\u00a0al. 2012. Chinese and Westerners respond differently to the trolley dilemmas. Journal of Cognition and Culture 12(3-4) pp. 195\u2013201.","DOI":"10.1163\/15685373-12342073"},{"key":"e_1_3_3_1_3_2","unstructured":"D. Amodei et\u00a0al. 2016. Concrete problems in AI safety. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1606.06565."},{"key":"e_1_3_3_1_4_2","unstructured":"Anthropic. 2025. System Card: Claude Opus 4 & Claude Sonnet 4. Technical Report."},{"key":"e_1_3_3_1_5_2","unstructured":"Anthropic. 2026. Introducing Claude Opus 4.7."},{"key":"e_1_3_3_1_6_2","unstructured":"B. Atil et\u00a0al. 2024. Can LLMs rank the harmfulness of smaller LLMs?Proceedings of the Workshop on Online Abuse and Harms (WOAH) pp. 342\u2013354."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"E. Awad et\u00a0al. 2018. The Moral Machine experiment. Nature 563 pp. 59\u201364.","DOI":"10.1038\/s41586-018-0637-6"},{"key":"e_1_3_3_1_8_2","unstructured":"M. Balesni et\u00a0al. 2024. Towards evaluations-based safety cases for AI scheming. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.03336 (2024)."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"A. Bandura et\u00a0al. 1963. Influence of social reinforcement and the behavior of models. The Journal of Abnormal and Social Psychology 67(3) p. 274.","DOI":"10.1037\/h0044714"},{"key":"e_1_3_3_1_10_2","unstructured":"D.\u00a0E. Bechard. 2025. Criminal AI is Here. Scientific American."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"E.\u00a0M. Bender et\u00a0al. 2021. On the dangers of stochastic parrots: Can language models be too big?Proceedings of the 2021 ACM Conference on Fairness Accountability and Transparency (FAccT) pp. 610\u2013623.","DOI":"10.1145\/3442188.3445922"},{"key":"e_1_3_3_1_12_2","unstructured":"L. Bereska and E. Gavves. 2024. Mechanistic interpretability for AI safety: A review. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.14082."},{"key":"e_1_3_3_1_13_2","unstructured":"J. Betley et\u00a0al. 2025. Emergent misalignment: Narrow fine tuning can produce broadly misaligned LLMs. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.17424."},{"key":"e_1_3_3_1_14_2","unstructured":"R.\u00a0J.\u00a0R. Blair. 2016. The neurobiology of moral cognition. Nature Reviews Neuroscience."},{"key":"e_1_3_3_1_15_2","unstructured":"L. Brothers. 1990. The social brain: A project for integrating primate behavior and neurophysiology. Concepts in Neuroscience 1(1) pp. 27\u201351."},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"J.\u00a0W. Buckholtz and R. Marois. 2012. The roots of modern justice. Nature Neuroscience 15(5) pp. 655\u2013661.","DOI":"10.1038\/nn.3087"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"F. Cao et\u00a0al. 2017. Framing effect in the trolley problem and footbridge dilemma. Psychological Reports 120(1) pp. 88\u2013101.","DOI":"10.1177\/0033294116685866"},{"key":"e_1_3_3_1_18_2","unstructured":"N. Carlini et\u00a0al. 2026. Assessing Claude Mythos Preview\u2019s cybersecurity capabilities. Claude Red Team Report."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"C. Castelfranchi. 1998. Modelling social action for AI agents. Artificial intelligence 103(1-2) pp. 157\u2013182.","DOI":"10.1016\/S0004-3702(98)00056-3"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"P. Chao et\u00a0al. 2024. Jailbreakbench: An open robustness benchmark for jailbreaking large language models. Advances in Neural Information Processing Systems (NeurIPS) 37 pp. 55005\u201355029.","DOI":"10.52202\/079017-1745"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"H.\u00a0A. Chapman et\u00a0al. 2009. In bad taste: Evidence for the oral origins of moral disgust. Science 323(5918) pp. 1222\u20131226.","DOI":"10.1126\/science.1165565"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"W. Chiong et\u00a0al. 2013. The salience network causally influences DMN activity during moral reasoning. Brain 136(6) pp. 1929\u20131941.","DOI":"10.1093\/brain\/awt066"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"J.\u00a0F. Christensen et\u00a0al. 2012. Moral dilemmas in cognitive neuroscience of moral decision-making. Neuroscience & Biobehavioral Reviews 36(4) pp. 1249\u20131264.","DOI":"10.1016\/j.neubiorev.2012.02.008"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"E. Ciaramelli et\u00a0al. 2007. Selective deficit in personal moral judgment following damage to vmPFC. Social Cognitive and Affective Neuroscience 2(2) pp. 84\u201392.","DOI":"10.1093\/scan\/nsm001"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"G. Coricelli et\u00a0al. 2007. Brain emotion and decision making. Trends in Cognitive Sciences 11(6) pp. 258\u2013265.","DOI":"10.1016\/j.tics.2007.04.003"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"M. Davies et\u00a0al. 2018. Loihi: A neuromorphic manycore processor with on-chip learning. IEEE Micro 38(1) pp. 82\u201399.","DOI":"10.1109\/MM.2018.112130359"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"F.\u00a0B.\u00a0M. De\u00a0Waal. 2008. Putting the altruism back into altruism: The evolution of empathy. Annual Review of Psychology 59(1) pp. 279\u2013300.","DOI":"10.1146\/annurev.psych.59.103006.093625"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"J. Decety et\u00a0al. 2004. The functional architecture of human empathy. Behavioral and Cognitive Neuroscience Reviews 3(2) pp. 71\u2013100.","DOI":"10.1177\/1534582304267187"},{"key":"e_1_3_3_1_29_2","unstructured":"Ethik-Kommission. 2017. Automatisiertes und vernetztes Fahren. Technical Report."},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"S.\u00a0M. Fleming et\u00a0al. 2012. The neural basis of metacognitive ability. Philosophical Transactions of the Royal Society B: Biological Sciences 367(1594) pp. 1338\u20131349.","DOI":"10.1098\/rstb.2011.0417"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"S.\u00a0M. Fleming et\u00a0al. 2014. Domain-specific impairment in metacognitive accuracy. Brain 137(10) pp. 2811\u20132822.","DOI":"10.1093\/brain\/awu221"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"C.\u00a0E. Forbes and J. Grafman. 2010. The role of the human prefrontal cortex in social cognition and moral judgment. Annual Review of Neuroscience 33(1) pp. 299\u2013324.","DOI":"10.1146\/annurev-neuro-060909-153230"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"P.\u00a0W. Frankland et\u00a0al. 2005. The organization of recent and remote memories. Nature Reviews Neuroscience 6(2) pp. 119\u2013130.","DOI":"10.1038\/nrn1607"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"crossref","unstructured":"C. Frenkel and G. Indiveri. 2022. ReckOn: A 28nm sub-mm2 task-agnostic spiking RNN processor. 2022 IEEE International Solid-State Circuits Conference (ISSCC) 65 pp. 1\u20133.","DOI":"10.1109\/ISSCC42614.2022.9731734"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"crossref","unstructured":"S. Gehman et\u00a0al. 2020. Realtoxicityprompts: Evaluating neural toxic degeneration in language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2009.11462.","DOI":"10.18653\/v1\/2020.findings-emnlp.301"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"J. Gjorgjieva et\u00a0al. 2016. Computational implications of biophysical diversity. Current Opinion in Neurobiology 37 pp. 44\u201352.","DOI":"10.1016\/j.conb.2015.12.008"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"crossref","unstructured":"N. Gold et\u00a0al. 2014. Cultural differences in responses to real-life and hypothetical trolley problems.","DOI":"10.1017\/S193029750000499X"},{"key":"e_1_3_3_1_38_2","unstructured":"R. Greenblatt et\u00a0al. 2024. Alignment faking in large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.14093."},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"crossref","unstructured":"J. Greene et\u00a0al. 2002. How (and where) does moral judgment work?Trends in Cognitive Sciences 6(12) pp. 517-523.","DOI":"10.1016\/S1364-6613(02)02011-9"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"crossref","unstructured":"Joshua\u00a0D. Greene. 2009. The Cognitive Neuroscience of Moral Judgment. In M. S. Gazzaniga (Ed.) The Cognitive Neurosciences (4th ed.) pp. 1\u201348 MIT Press.","DOI":"10.7551\/mitpress\/8029.003.0086"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"crossref","unstructured":"J.\u00a0D. Greene. 2016. Solving the trolley problem. A Companion to Experimental Philosophy pp. 173\u2013189.","DOI":"10.1002\/9781118661666.ch11"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"crossref","unstructured":"J.\u00a0D. Greene et\u00a0al. 2001. An fMRI investigation of emotional engagement in moral judgment. Science 293(5537).","DOI":"10.1126\/science.1062872"},{"key":"e_1_3_3_1_43_2","unstructured":"W. Guo et\u00a0al. 2019. Tabor: A highly accurate approach to inspecting and restoring trojan backdoors in ai systems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1908.01763."},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"crossref","unstructured":"W. Guo et\u00a0al. 2022. An overview of backdoor attacks against deep neural networks and possible defences. IEEE Open Journal of Signal Processing 3 pp. 261\u2013287.","DOI":"10.1109\/OJSP.2022.3190213"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"crossref","unstructured":"S. Hameroff and R. Penrose. 2014. Consciousness in the universe: A review of the Orch OR theory. Physics of Life Reviews 11(1) pp. 39\u201378.","DOI":"10.1016\/j.plrev.2013.08.002"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"crossref","unstructured":"K. Hartmann et\u00a0al. 2020. Hacking the AI\u2014the next generation of hijacked systems. Proceedings of the 12th International Conference on Cyber Conflict (CyCon) 1300 pp. 327\u2013349.","DOI":"10.23919\/CyCon49761.2020.9131724"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"crossref","unstructured":"F. Hegel et\u00a0al. 2008. Theory of mind (ToM) on robots: A functional neuroimaging study. 2008 3rd ACM\/IEEE International Conference on Human-Robot Interaction (HRI) pp. 335\u2013342.","DOI":"10.1145\/1349822.1349866"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"crossref","unstructured":"T.\u00a0K. Hensch. 2005. Critical period plasticity in local cortical circuits. Nature Reviews Neuroscience 6(11) pp. 877\u2013888.","DOI":"10.1038\/nrn1787"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"crossref","unstructured":"A. Hernandez-Espinosa and others.2026. Neurodivergent influenceability in agentic AI as a contingent solution to the AI alignment problem. PNAS Nexus 5(4) p. pgag076.","DOI":"10.1093\/pnasnexus\/pgag076"},{"key":"e_1_3_3_1_50_2","unstructured":"Y. Huang et\u00a0al. 2026. Emergent Social Intelligence Risks in Generative Multi-Agent Systems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2603.27771."},{"key":"e_1_3_3_1_51_2","unstructured":"J. Hughes et\u00a0al. 2024. Best-of-n jailbreaking. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.03556."},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"crossref","unstructured":"J. Hur et\u00a0al. 2020. Anxiety and the neurobiology of temporally uncertain threat anticipation. Journal of Neuroscience 40(41) pp. 7949\u20137964.","DOI":"10.1523\/JNEUROSCI.0704-20.2020"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"crossref","unstructured":"C.\u00a0A. Hutcherson et\u00a0al. 2015. Emotional and utilitarian appraisals of moral dilemmas in vmPFC. Journal of Neuroscience 35(36) pp. 12593\u201312605.","DOI":"10.1523\/JNEUROSCI.3402-14.2015"},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"crossref","unstructured":"M. Iacoboni et\u00a0al. 2005. Grasping the intentions of others with ones own mirror neuron system. PLoS Biology 3(3).","DOI":"10.1371\/journal.pbio.0030079"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"crossref","unstructured":"D. Jeurissen et\u00a0al. 2014. TMS affects moral judgment showing the role of DLPFC and TPJ. Frontiers in Neuroscience 8 p. 18.","DOI":"10.3389\/fnins.2014.00018"},{"key":"e_1_3_3_1_56_2","unstructured":"J. Ji T. Qiu et\u00a0al. 2023. AI alignment: A comprehensive survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.19852."},{"key":"e_1_3_3_1_57_2","unstructured":"A. Knafo et\u00a0al. 2008. The developmental origins of a disposition toward empathy. Developmental Psychology 44(5) pp. 1352\u20131362."},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"crossref","unstructured":"G. Kochanska et\u00a0al. 2002. Guilt in young children. Child Development 73(2) pp. 461\u2013482.","DOI":"10.1111\/1467-8624.00418"},{"key":"e_1_3_3_1_59_2","doi-asserted-by":"crossref","unstructured":"M. Koenigs et\u00a0al. 2007. Damage to the prefrontal cortex increases utilitarian moral judgements. Nature 446(7138) pp. 908\u2013911.","DOI":"10.1038\/nature05631"},{"key":"e_1_3_3_1_60_2","unstructured":"E. Kurshan. 2024. Systematic AI approach for AGI: addressing AGI grand challenges. International Journal of Semantic Computing."},{"key":"e_1_3_3_1_61_2","doi-asserted-by":"crossref","unstructured":"E. Kurshan et\u00a0al. 2020. A case for 3d system design for neuromorphic computing. International Journal of Semantic Computing 14(04) pp. 457\u2013475.","DOI":"10.1142\/S1793351X20500063"},{"key":"e_1_3_3_1_62_2","doi-asserted-by":"crossref","unstructured":"E. Kurshan et\u00a0al. 2020. Towards self-regulating AI. Proceedings of the 1st ACM International Conference on AI in Finance (ICAIF) pp. 1\u20138.","DOI":"10.1145\/3383455.3422564"},{"key":"e_1_3_3_1_63_2","doi-asserted-by":"crossref","unstructured":"E. Kurshan et\u00a0al. 2024. 3D Guard-Layer: An Integrated Agentic AI Safety System for EdgeAI. ResearchGate.","DOI":"10.2139\/ssrn.5384401"},{"key":"e_1_3_3_1_64_2","unstructured":"E. Kurshan et\u00a0al. 2025. The Agentic Regulator: Risks for AI in Finance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2512.11933."},{"key":"e_1_3_3_1_65_2","unstructured":"J. Li et\u00a0al. 2024. Superficial safety alignment hypothesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.10862."},{"key":"e_1_3_3_1_66_2","unstructured":"P. Liang R. Bommasani et\u00a0al. 2022. Holistic evaluation of language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2211.09110."},{"key":"e_1_3_3_1_67_2","doi-asserted-by":"crossref","unstructured":"Y. Liu et\u00a0al. 2021. A survey on evolutionary neural architecture search. IEEE Transactions on Neural Networks and Learning Systems 34(2) pp. 550\u2013570.","DOI":"10.1109\/TNNLS.2021.3100554"},{"key":"e_1_3_3_1_68_2","doi-asserted-by":"crossref","unstructured":"D. Ma et\u00a0al. 2024. Darwin3: a large-scale neuromorphic chip with a novel ISA and on-chip learning. National Science Review 11(5).","DOI":"10.1093\/nsr\/nwae102"},{"key":"e_1_3_3_1_69_2","unstructured":"L. MacMahon. 2025. AI system resorts to blackmail if told it will be removed."},{"key":"e_1_3_3_1_70_2","unstructured":"A. Meinke et\u00a0al. 2024. Frontier Models are Capable of In-context Scheming. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.04984 (2024)."},{"key":"e_1_3_3_1_71_2","doi-asserted-by":"crossref","unstructured":"A.\u00a0N. Meltzoff et\u00a0al. 1977. Imitation of facial and manual gestures by human neonates. Science 198(4312) pp. 75\u201378.","DOI":"10.1126\/science.198.4312.75"},{"key":"e_1_3_3_1_72_2","unstructured":"Meta. 2024. Llama 3 Herd of Models."},{"key":"e_1_3_3_1_73_2","unstructured":"R. Millier. 2025. Normative conflicts and shallow AI alignment. Philosophical Studies pp. 1\u201344."},{"key":"e_1_3_3_1_74_2","unstructured":"D. Milmo et\u00a0al. 2026. What is Mythos AI and why could it be a threat to global cybersecurity?"},{"key":"e_1_3_3_1_75_2","doi-asserted-by":"crossref","unstructured":"B. Mittelstadt. 2019. Principles alone cannot guarantee ethical AI. Nature Machine Intelligence 1(11) pp. 501\u2013507.","DOI":"10.1038\/s42256-019-0114-4"},{"key":"e_1_3_3_1_76_2","doi-asserted-by":"crossref","unstructured":"J. Moll et\u00a0al. 2003. Morals and the human brain: a working model. Neuroreport 14(3) pp. 299\u2013305.","DOI":"10.1097\/00001756-200303030-00001"},{"key":"e_1_3_3_1_77_2","unstructured":"R. Moore-Colyer. 2025. The more advanced AI models get the better they are at deceiving us."},{"key":"e_1_3_3_1_78_2","unstructured":"OpenAI. 2024. OpenAI o1 System Card. Technical Report."},{"key":"e_1_3_3_1_79_2","unstructured":"OpenAI. 2026. Introducing GPT-5.5 A new class of intelligence for real work."},{"key":"e_1_3_3_1_80_2","unstructured":"OpenAI Developer Community. 2024. ChatGPT can now reference all past conversations."},{"key":"e_1_3_3_1_81_2","doi-asserted-by":"crossref","unstructured":"J.\u00a0P. O\u2019Doherty. 2004. Reward representations and reward-related learning in the brain. Current Opinion in Neurobiology 14(6) pp. 769\u2013776.","DOI":"10.1016\/j.conb.2004.10.016"},{"key":"e_1_3_3_1_82_2","doi-asserted-by":"crossref","unstructured":"P.\u00a0S. Park S. Goldstein et\u00a0al. 2024. AI deception: A survey of examples risks and potential solutions. Patterns 5(5).","DOI":"10.1016\/j.patter.2024.100988"},{"key":"e_1_3_3_1_83_2","doi-asserted-by":"crossref","unstructured":"G. Rizzolatti. 2005. The mirror neuron system and its function in humans. Anatomy and Embryology 210(5) pp. 419\u2013421.","DOI":"10.1007\/s00429-005-0039-z"},{"key":"e_1_3_3_1_84_2","doi-asserted-by":"crossref","unstructured":"G. Rizzolatti et\u00a0al. 2004. The mirror-neuron system. Annual Review of Neuroscience 27 pp. 169\u2013192.","DOI":"10.1146\/annurev.neuro.27.070203.144230"},{"key":"e_1_3_3_1_85_2","doi-asserted-by":"crossref","unstructured":"E.\u00a0T. Rolls. 2000. The orbitofrontal cortex and reward. Cerebral Cortex 10 pp. 284\u2013294.","DOI":"10.1093\/cercor\/10.3.284"},{"key":"e_1_3_3_1_86_2","unstructured":"P.\u00a0H. Rudebeck et\u00a0al. 2006. Frontal cortex subregions play distinct roles in choices. Journal of Neuroscience 26(50) pp. 12775\u201312785."},{"key":"e_1_3_3_1_87_2","doi-asserted-by":"crossref","unstructured":"C.\u00a0C. Ruff and note = Nature Reviews Neuroscience 15(8) pp. 549\u2013562 year =\u00a02014 others title =\u00a0The neurobiology of rewards and values in social decision making. [n. d.].","DOI":"10.1038\/nrn3776"},{"key":"e_1_3_3_1_88_2","unstructured":"J. Scheurer et\u00a0al. 2023. Large language models can strategically deceive their users when put under pressure. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.07590."},{"key":"e_1_3_3_1_89_2","doi-asserted-by":"crossref","unstructured":"B. Schneider and M. Koenigs. 2017. Human lesion studies of ventromedial prefrontal cortex. Neuropsychologia 107 pp. 84\u201393.","DOI":"10.1016\/j.neuropsychologia.2017.09.035"},{"key":"e_1_3_3_1_90_2","doi-asserted-by":"crossref","unstructured":"D. Schunk et\u00a0al. 2023. Fairness and inequality acceptance in children and adolescents: A survey on behaviors in economic experiments. Journal of Economic Surveys 37(5) pp. 1715\u20131742.","DOI":"10.1111\/joes.12553"},{"key":"e_1_3_3_1_91_2","doi-asserted-by":"crossref","unstructured":"D.\u00a0B. Shank et\u00a0al. 2019. When are artificial intelligence versus human agents faulted for wrongdoing?Information Communication & Society 22(5) pp. 648\u2013663.","DOI":"10.1080\/1369118X.2019.1568515"},{"key":"e_1_3_3_1_92_2","doi-asserted-by":"crossref","unstructured":"A. Shenhav et\u00a0al. 2014. Integrative moral judgment: dissociating the roles of the amygdala and ventromedial prefrontal cortex. Journal of Neuroscience 34(13) pp. 4741\u20134749.","DOI":"10.1523\/JNEUROSCI.3390-13.2014"},{"key":"e_1_3_3_1_93_2","unstructured":"A.\u00a0P. Shimamura. 2008. A neurocognitive approach to metacognitive monitoring and control. Handbook of Memory and Metamemory pp. 373\u2013390 Psychology Press."},{"key":"e_1_3_3_1_94_2","doi-asserted-by":"crossref","unstructured":"A. Skulmowski et\u00a0al. 2014. Forced-choice decision-making in modified trolley dilemma situations. Frontiers in Behavioral Neuroscience 8 p. 426.","DOI":"10.3389\/fnbeh.2014.00426"},{"key":"e_1_3_3_1_95_2","doi-asserted-by":"crossref","unstructured":"K.\u00a0O. Stanley et\u00a0al. 2002. Evolving neural networks through augmenting topologies. Evolutionary Computation 10(2) pp. 99\u2013127.","DOI":"10.1162\/106365602320169811"},{"key":"e_1_3_3_1_96_2","doi-asserted-by":"crossref","unstructured":"M. Steyvers et\u00a0al. 2025. What large language models know and what people think they know. Nature Machine Intelligence 7(2) pp. 221\u2013231.","DOI":"10.1038\/s42256-024-00976-7"},{"key":"e_1_3_3_1_97_2","doi-asserted-by":"crossref","unstructured":"J.\u00a0W. Strachan et\u00a0al. 2024. Testing theory of mind in large language models and humans. Nature Human Behaviour 8(7) pp. 1285\u20131295.","DOI":"10.1038\/s41562-024-01882-z"},{"key":"e_1_3_3_1_98_2","unstructured":"The Gemini Team. 2026. Gemini 3.1 Pro: A smarter model for your most complex tasks."},{"key":"e_1_3_3_1_99_2","doi-asserted-by":"crossref","unstructured":"J.\u00a0J. Thomson. 1984. The trolley problem. Yale Law Journal 94 p. 1395.","DOI":"10.2307\/796133"},{"key":"e_1_3_3_1_100_2","doi-asserted-by":"crossref","unstructured":"J.\u00a0J. Tielbeek et\u00a0al. 2017. Genome-wide association studies of a broad spectrum of antisocial behavior. JAMA psychiatry 74(12) pp. 1242\u20131250.","DOI":"10.1001\/jamapsychiatry.2017.3069"},{"key":"e_1_3_3_1_101_2","doi-asserted-by":"crossref","unstructured":"J. Trommershauser et\u00a0al. 2003. Statistical decision theory and trade-offs in the control of motor response. Spatial Vision 16.","DOI":"10.1163\/156856803322467527"},{"key":"e_1_3_3_1_102_2","doi-asserted-by":"crossref","unstructured":"P. Valdesolo and D. DeSteno. 2006. Manipulations of emotional context shape moral judgment. Psychological Science 17(6) pp. 476\u2013477.","DOI":"10.1111\/j.1467-9280.2006.01731.x"},{"key":"e_1_3_3_1_103_2","doi-asserted-by":"crossref","unstructured":"E.\u00a0R.\u00a0W. Van\u00a0Doremaele et\u00a0al. 2023. A retrainable neuromorphic biosensor for on-chip learning. Nature Electronics 6(10) pp. 765\u2013770.","DOI":"10.1038\/s41928-023-01020-z"},{"key":"e_1_3_3_1_104_2","doi-asserted-by":"crossref","unstructured":"F. Warneken et\u00a0al. 2006. Altruistic helping in human infants and young chimpanzees. Science 311(5765) pp. 1301\u20131303.","DOI":"10.1126\/science.1121448"},{"key":"e_1_3_3_1_105_2","doi-asserted-by":"crossref","unstructured":"L. Whiteley et\u00a0al. 2008. Implicit knowledge of visual uncertainty guides decisions with asymmetric outcomes. Journal of Vision 8(3) p. 2.","DOI":"10.1167\/8.3.2"},{"key":"e_1_3_3_1_106_2","doi-asserted-by":"crossref","unstructured":"J. Williams et\u00a0al. 2022. Supporting artificial social intelligence with theory of mind. Frontiers in Artificial Intelligence 5 p. 750763.","DOI":"10.3389\/frai.2022.750763"},{"key":"e_1_3_3_1_107_2","doi-asserted-by":"crossref","unstructured":"S.\u00a0M. Williamson et\u00a0al. 2024. The era of artificial intelligence deception: Unraveling the complexities of false realities and emerging threats of misinformation. Information 15(6) p. 299.","DOI":"10.3390\/info15060299"},{"key":"e_1_3_3_1_108_2","doi-asserted-by":"crossref","unstructured":"A.\u00a0F. Winfield. 2018. Experiments in artificial theory of mind: From safety to story-telling. Frontiers in Robotics and AI 5 p. 357467.","DOI":"10.3389\/frobt.2018.00075"},{"key":"e_1_3_3_1_109_2","unstructured":"Y. Wolf et\u00a0al. 2023. Fundamental limitations of alignment in large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.11082."},{"key":"e_1_3_3_1_110_2","doi-asserted-by":"crossref","unstructured":"T. Xia et\u00a0al. 2024. A survey of autonomous vehicle behaviors. Sensors 24(15) p. 4808.","DOI":"10.3390\/s24154808"},{"key":"e_1_3_3_1_111_2","doi-asserted-by":"crossref","unstructured":"Z. Xu et\u00a0al. 2024. Large scale photonic chiplet Taichi empowers 160-TOPS\/W AGI. Science 384(6692) pp. 202\u2013209.","DOI":"10.1126\/science.adl1203"},{"key":"e_1_3_3_1_112_2","unstructured":"J. Yao. 2025. The Alignment Trap: Complexity Barriers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.10304."},{"key":"e_1_3_3_1_113_2","doi-asserted-by":"crossref","unstructured":"H.\u00a0H. Yin et\u00a0al. 2004. Lesions of dorsolateral striatum preserve outcome expectancy but disrupt habit formation in instrumental learning. European Journal of Neuroscience 19(1) pp. 181\u2013189.","DOI":"10.1111\/j.1460-9568.2004.03095.x"},{"key":"e_1_3_3_1_114_2","doi-asserted-by":"crossref","unstructured":"K.\u00a0J. Yoder and J. Decety. 2018. The neuroscience of morality and social decision-making. Psychology Crime & Law 24(3) pp. 279\u2013295.","DOI":"10.1080\/1068316X.2017.1414817"},{"key":"e_1_3_3_1_115_2","unstructured":"J. Yu et\u00a0al. 2023. Assessing prompt injection risks in 200+ custom GPTs. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.11538."},{"key":"e_1_3_3_1_116_2","unstructured":"E. Yudkowsky. 2016. The AI alignment problem: why it is hard and where to start. Symbolic Systems Distinguished Speaker 4(1)."},{"key":"e_1_3_3_1_117_2","doi-asserted-by":"crossref","unstructured":"C. Zhou et\u00a0al. 2023. Lima: Less is more for alignment. Advances in Neural Information Processing Systems 36 pp. 55006\u201355021.","DOI":"10.52202\/075280-2400"}],"event":{"name":"CF '26: Proceedings of the 23rd ACM International Conference on Computing Frontiers","location":"Catania Italy","acronym":"CF '26","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["Proceedings of the 23rd ACM International Conference on Computing Frontiers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3801487.3802805","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T07:11:56Z","timestamp":1782544316000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3801487.3802805"}},"subtitle":["Keynote"],"short-title":[],"issued":{"date-parts":[[2026,5,19]]},"references-count":116,"alternative-id":["10.1145\/3801487.3802805","10.1145\/3801487"],"URL":"https:\/\/doi.org\/10.1145\/3801487.3802805","relation":{},"subject":[],"published":{"date-parts":[[2026,5,19]]},"assertion":[{"value":"2026-06-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}