{"id":9941,"date":"2025-02-18T12:51:58","date_gmt":"2025-02-18T12:51:58","guid":{"rendered":"https:\/\/www.maschinenethik.net\/?p=9941"},"modified":"2025-02-18T13:10:49","modified_gmt":"2025-02-18T13:10:49","slug":"revisiting-the-trolley-problem-for-ai","status":"publish","type":"post","link":"https:\/\/www.maschinenethik.net\/?p=9941","title":{"rendered":"Revisiting the Trolley Problem for AI"},"content":{"rendered":"<p><span data-teams=\"true\">The paper \u201cRevisiting the Trolley Problem for AI: Biases and Stereotypes in Large Language Models and their Impact on Ethical Decision-Making&#8220; by Sahan Hatemo, Christof Weickhardt, Luca Gisler (FHNW School of Computer Science), and Oliver Bendel (FHNW School of Business) was accepted at the AAAI 2025 Spring Symposium &#8222;Human-Compatible AI for Well-being: Harnessing Potential of GenAI for AI-Powered Science&#8220;.\u00a0A year ago, Sahan Hatemo had already dedicated himself to the topic of &#8222;ETHICAL DECISION MAKING OF AI: An Investigation Using a Stereotyped Persona Approach in the Trolley Problem&#8220; in a so-called <a href=\"https:\/\/www.informationsethik.net\/wie-entscheidet-ein-llm-beim-trolley-problem\/\">mini-challenge<\/a> in the Data Science degree program. His supervisor, Oliver Bendel, had told the other scientists about the idea at the AAAI 2025 Spring Symposium &#8222;Impact of GenAI on Social and Individual Well-being&#8220; at Stanford University. This led to a lively discussion. The student recruited two colleagues, Christof Weickhardt and Luca Gisler, and worked on the topic in a much more complex form in a so-called Challenge X. This time, three different open-source language models were applied to the trolley problem. In each case, personalities were created with nationality, gender, and age. In addition, the data was compared with that of the MIT Moral Machine project. Sahan Hatemo, Christof Weickhardt, and Luca Gisler will present their results at the end of March or beginning of April 2025 in San Francisco, the venue of this year&#8217;s event.<\/span><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-9943\" src=\"https:\/\/www.maschinenethik.net\/wp-content\/uploads\/2025\/02\/Trolley_Problem.png\" alt=\"\" width=\"1164\" height=\"470\" srcset=\"https:\/\/www.maschinenethik.net\/wp-content\/uploads\/2025\/02\/Trolley_Problem.png 1164w, https:\/\/www.maschinenethik.net\/wp-content\/uploads\/2025\/02\/Trolley_Problem-300x121.png 300w, https:\/\/www.maschinenethik.net\/wp-content\/uploads\/2025\/02\/Trolley_Problem-1024x413.png 1024w, https:\/\/www.maschinenethik.net\/wp-content\/uploads\/2025\/02\/Trolley_Problem-768x310.png 768w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><\/p>\n<p>Fig.: Variants of the trolley problem (Image: Jonas Kubilius)<\/p>\n","protected":false},"excerpt":{"rendered":"<p>The paper \u201cRevisiting the Trolley Problem for AI: Biases and Stereotypes in Large Language Models and their Impact on Ethical Decision-Making&#8220; by Sahan Hatemo, Christof Weickhardt, Luca Gisler (FHNW School of Computer Science), and Oliver Bendel (FHNW School of Business) was accepted at the AAAI 2025 Spring Symposium &#8222;Human-Compatible AI for Well-being: Harnessing Potential of &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/www.maschinenethik.net\/?p=9941\" class=\"more-link\"><span class=\"screen-reader-text\">\u201eRevisiting the Trolley Problem for AI\u201c <\/span>weiterlesen<\/a><\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1129,886],"tags":[168,169,1529,1440,1612,540],"class_list":["post-9941","post","type-post","status-publish","format-standard","hentry","category-ki-ethik","category-kuenstliche-intelligenz","tag-ai","tag-artificial-intelligence","tag-genai","tag-llm","tag-llms","tag-trolley-problem"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.8 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Revisiting the Trolley Problem for AI - maschinenethik.net<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.maschinenethik.net\/?p=9941\" \/>\n<meta property=\"og:locale\" content=\"de_DE\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Revisiting the Trolley Problem for AI - maschinenethik.net\" \/>\n<meta property=\"og:description\" content=\"The paper \u201cRevisiting the Trolley Problem for AI: Biases and Stereotypes in Large Language Models and their Impact on Ethical Decision-Making&#8220; by Sahan Hatemo, Christof Weickhardt, Luca Gisler (FHNW School of Computer Science), and Oliver Bendel (FHNW School of Business) was accepted at the AAAI 2025 Spring Symposium &#8222;Human-Compatible AI for Well-being: Harnessing Potential of &hellip; \u201eRevisiting the Trolley Problem for AI\u201c weiterlesen\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.maschinenethik.net\/?p=9941\" \/>\n<meta property=\"og:site_name\" content=\"maschinenethik.net\" \/>\n<meta property=\"article:published_time\" content=\"2025-02-18T12:51:58+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-02-18T13:10:49+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.maschinenethik.net\/wp-content\/uploads\/2025\/02\/Trolley_Problem.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1164\" \/>\n\t<meta property=\"og:image:height\" content=\"470\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"bendelo\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Verfasst von\" \/>\n\t<meta name=\"twitter:data1\" content=\"bendelo\" \/>\n\t<meta name=\"twitter:label2\" content=\"Gesch\u00e4tzte Lesezeit\" \/>\n\t<meta name=\"twitter:data2\" content=\"2\u00a0Minuten\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/www.maschinenethik.net\\\/?p=9941#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.maschinenethik.net\\\/?p=9941\"},\"author\":{\"name\":\"bendelo\",\"@id\":\"https:\\\/\\\/www.maschinenethik.net\\\/#\\\/schema\\\/person\\\/8bb3eb6ac670c6232634a22d062cae95\"},\"headline\":\"Revisiting the Trolley Problem for AI\",\"datePublished\":\"2025-02-18T12:51:58+00:00\",\"dateModified\":\"2025-02-18T13:10:49+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/www.maschinenethik.net\\\/?p=9941\"},\"wordCount\":240,\"image\":{\"@id\":\"https:\\\/\\\/www.maschinenethik.net\\\/?p=9941#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.maschinenethik.net\\\/wp-content\\\/uploads\\\/2025\\\/02\\\/Trolley_Problem.png\",\"keywords\":[\"AI\",\"Artificial Intelligence\",\"GenAI\",\"LLM\",\"LLMs\",\"Trolley-Problem\"],\"articleSection\":[\"KI-Ethik\",\"K\u00fcnstliche Intelligenz\"],\"inLanguage\":\"de\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.maschinenethik.net\\\/?p=9941\",\"url\":\"https:\\\/\\\/www.maschinenethik.net\\\/?p=9941\",\"name\":\"Revisiting the Trolley Problem for AI - maschinenethik.net\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.maschinenethik.net\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/www.maschinenethik.net\\\/?p=9941#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/www.maschinenethik.net\\\/?p=9941#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.maschinenethik.net\\\/wp-content\\\/uploads\\\/2025\\\/02\\\/Trolley_Problem.png\",\"datePublished\":\"2025-02-18T12:51:58+00:00\",\"dateModified\":\"2025-02-18T13:10:49+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/www.maschinenethik.net\\\/#\\\/schema\\\/person\\\/8bb3eb6ac670c6232634a22d062cae95\"},\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.maschinenethik.net\\\/?p=9941#breadcrumb\"},\"inLanguage\":\"de\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.maschinenethik.net\\\/?p=9941\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"de\",\"@id\":\"https:\\\/\\\/www.maschinenethik.net\\\/?p=9941#primaryimage\",\"url\":\"https:\\\/\\\/www.maschinenethik.net\\\/wp-content\\\/uploads\\\/2025\\\/02\\\/Trolley_Problem.png\",\"contentUrl\":\"https:\\\/\\\/www.maschinenethik.net\\\/wp-content\\\/uploads\\\/2025\\\/02\\\/Trolley_Problem.png\",\"width\":1164,\"height\":470},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.maschinenethik.net\\\/?p=9941#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Startseite\",\"item\":\"https:\\\/\\\/www.maschinenethik.net\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Revisiting the Trolley Problem for AI\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.maschinenethik.net\\\/#website\",\"url\":\"https:\\\/\\\/www.maschinenethik.net\\\/\",\"name\":\"maschinenethik.net\",\"description\":\"VON OLIVER BENDEL\",\"alternateName\":\"Maschinenethik\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.maschinenethik.net\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"de\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/www.maschinenethik.net\\\/#\\\/schema\\\/person\\\/8bb3eb6ac670c6232634a22d062cae95\",\"name\":\"bendelo\",\"url\":\"https:\\\/\\\/www.maschinenethik.net\\\/?author=3\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Revisiting the Trolley Problem for AI - maschinenethik.net","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.maschinenethik.net\/?p=9941","og_locale":"de_DE","og_type":"article","og_title":"Revisiting the Trolley Problem for AI - maschinenethik.net","og_description":"The paper \u201cRevisiting the Trolley Problem for AI: Biases and Stereotypes in Large Language Models and their Impact on Ethical Decision-Making&#8220; by Sahan Hatemo, Christof Weickhardt, Luca Gisler (FHNW School of Computer Science), and Oliver Bendel (FHNW School of Business) was accepted at the AAAI 2025 Spring Symposium &#8222;Human-Compatible AI for Well-being: Harnessing Potential of &hellip; \u201eRevisiting the Trolley Problem for AI\u201c weiterlesen","og_url":"https:\/\/www.maschinenethik.net\/?p=9941","og_site_name":"maschinenethik.net","article_published_time":"2025-02-18T12:51:58+00:00","article_modified_time":"2025-02-18T13:10:49+00:00","og_image":[{"width":1164,"height":470,"url":"https:\/\/www.maschinenethik.net\/wp-content\/uploads\/2025\/02\/Trolley_Problem.png","type":"image\/png"}],"author":"bendelo","twitter_card":"summary_large_image","twitter_misc":{"Verfasst von":"bendelo","Gesch\u00e4tzte Lesezeit":"2\u00a0Minuten"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.maschinenethik.net\/?p=9941#article","isPartOf":{"@id":"https:\/\/www.maschinenethik.net\/?p=9941"},"author":{"name":"bendelo","@id":"https:\/\/www.maschinenethik.net\/#\/schema\/person\/8bb3eb6ac670c6232634a22d062cae95"},"headline":"Revisiting the Trolley Problem for AI","datePublished":"2025-02-18T12:51:58+00:00","dateModified":"2025-02-18T13:10:49+00:00","mainEntityOfPage":{"@id":"https:\/\/www.maschinenethik.net\/?p=9941"},"wordCount":240,"image":{"@id":"https:\/\/www.maschinenethik.net\/?p=9941#primaryimage"},"thumbnailUrl":"https:\/\/www.maschinenethik.net\/wp-content\/uploads\/2025\/02\/Trolley_Problem.png","keywords":["AI","Artificial Intelligence","GenAI","LLM","LLMs","Trolley-Problem"],"articleSection":["KI-Ethik","K\u00fcnstliche Intelligenz"],"inLanguage":"de"},{"@type":"WebPage","@id":"https:\/\/www.maschinenethik.net\/?p=9941","url":"https:\/\/www.maschinenethik.net\/?p=9941","name":"Revisiting the Trolley Problem for AI - maschinenethik.net","isPartOf":{"@id":"https:\/\/www.maschinenethik.net\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.maschinenethik.net\/?p=9941#primaryimage"},"image":{"@id":"https:\/\/www.maschinenethik.net\/?p=9941#primaryimage"},"thumbnailUrl":"https:\/\/www.maschinenethik.net\/wp-content\/uploads\/2025\/02\/Trolley_Problem.png","datePublished":"2025-02-18T12:51:58+00:00","dateModified":"2025-02-18T13:10:49+00:00","author":{"@id":"https:\/\/www.maschinenethik.net\/#\/schema\/person\/8bb3eb6ac670c6232634a22d062cae95"},"breadcrumb":{"@id":"https:\/\/www.maschinenethik.net\/?p=9941#breadcrumb"},"inLanguage":"de","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.maschinenethik.net\/?p=9941"]}]},{"@type":"ImageObject","inLanguage":"de","@id":"https:\/\/www.maschinenethik.net\/?p=9941#primaryimage","url":"https:\/\/www.maschinenethik.net\/wp-content\/uploads\/2025\/02\/Trolley_Problem.png","contentUrl":"https:\/\/www.maschinenethik.net\/wp-content\/uploads\/2025\/02\/Trolley_Problem.png","width":1164,"height":470},{"@type":"BreadcrumbList","@id":"https:\/\/www.maschinenethik.net\/?p=9941#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Startseite","item":"https:\/\/www.maschinenethik.net\/"},{"@type":"ListItem","position":2,"name":"Revisiting the Trolley Problem for AI"}]},{"@type":"WebSite","@id":"https:\/\/www.maschinenethik.net\/#website","url":"https:\/\/www.maschinenethik.net\/","name":"maschinenethik.net","description":"VON OLIVER BENDEL","alternateName":"Maschinenethik","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.maschinenethik.net\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"de"},{"@type":"Person","@id":"https:\/\/www.maschinenethik.net\/#\/schema\/person\/8bb3eb6ac670c6232634a22d062cae95","name":"bendelo","url":"https:\/\/www.maschinenethik.net\/?author=3"}]}},"_links":{"self":[{"href":"https:\/\/www.maschinenethik.net\/index.php?rest_route=\/wp\/v2\/posts\/9941","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.maschinenethik.net\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.maschinenethik.net\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.maschinenethik.net\/index.php?rest_route=\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/www.maschinenethik.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=9941"}],"version-history":[{"count":3,"href":"https:\/\/www.maschinenethik.net\/index.php?rest_route=\/wp\/v2\/posts\/9941\/revisions"}],"predecessor-version":[{"id":9945,"href":"https:\/\/www.maschinenethik.net\/index.php?rest_route=\/wp\/v2\/posts\/9941\/revisions\/9945"}],"wp:attachment":[{"href":"https:\/\/www.maschinenethik.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=9941"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.maschinenethik.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=9941"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.maschinenethik.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=9941"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}