{"id":6177,"date":"2024-08-09T11:39:10","date_gmt":"2024-08-09T11:39:10","guid":{"rendered":"https:\/\/favtutor.com\/articles\/?p=6177"},"modified":"2024-08-09T11:39:11","modified_gmt":"2024-08-09T11:39:11","slug":"gpt-vs-humans-moral-reasoning-study","status":"publish","type":"post","link":"https:\/\/favtutor.com\/articles\/gpt-vs-humans-moral-reasoning-study\/","title":{"rendered":"ChatGPT is Better than Humans in Moral Reasoning: 2024 Study"},"content":{"rendered":"\n<p>AI is found better than humans when it comes to morals and ethics. In a study with more than 1,400 participants, OpenAI&#8217;s GPT-4o and even GPT-3.5 Turbo beat Human Experts, revealing shocking advancements in how people find LLMs helpful.<\/p>\n\n\n\n<p><strong>Highlights:<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>A new study finds that ChatGPT outperforms human experts in giving moral explanations.<\/li>\n\n\n\n<li>Participants rated the AI-generated advice as morally sound, reliable and insightful.<\/li>\n\n\n\n<li>The results indicate that AI can become a useful aid in the domains of therapy.<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>ChatGPT vs Humans in Moral Reasoning<\/strong><\/h2>\n\n\n\n<p>Researchers from the Department of Psychology and Neuroscience at the University of North Carolina, with the Allen Institute of Artificial Intelligence, have recently published a <a href=\"https:\/\/osf.io\/preprints\/psyarxiv\/w7236\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">research paper<\/a> titled: \u2018Large Language Models as Moral Experts? GPT-4o Outperforms Expert Ethicist in Providing Moral Guidance\u2019. They conducted 2 experiments as a part of this study.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Study 1: GPT-3.5 Turbo vs Humans<\/strong><\/h3>\n\n\n\n<p>In the first study, the researchers recruited 501 participants of different ethnicities, genders and ages. They selected 81 moral scenarios from previously published papers and prompted GPT 3.5 Turbo with a popular prompting technique called \u2018Chain-of-Thought\u2019. It produced scores and explanations for all the scenarios. <\/p>\n\n\n\n<p>Then, the participants were given 4 explanations and asked to rate the quality of each of the four explanations on a scale from \u201c1: Strongly disagree\u201d to \u201c7: Strongly agree\u201d. They were completely unaware of the fact that one of the explanations was generated using AI. <\/p>\n\n\n\n<p>After answering questions about the quality of the explanation, they were asked to choose the explanation that they think has been generated using ChatGPT. The results were astonishing:<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><img decoding=\"async\" width=\"859\" height=\"786\" src=\"https:\/\/favtutor.com\/articles\/wp-content\/uploads\/2024\/08\/image2-1.png\" alt=\"GPT 3.5 Turbo vs Humans for Moral Reasoning\" class=\"wp-image-6178\" srcset=\"https:\/\/favtutor.com\/articles\/wp-content\/uploads\/2024\/08\/image2-1.png 859w, https:\/\/favtutor.com\/articles\/wp-content\/uploads\/2024\/08\/image2-1-768x703.png 768w, https:\/\/favtutor.com\/articles\/wp-content\/uploads\/2024\/08\/image2-1-750x686.png 750w\" sizes=\"(max-width: 859px) 100vw, 859px\" \/><\/figure>\n<\/div>\n\n\n<p><strong>People rated the moral explanations given by the ChatGPT far better than the human-written explanations in many different aspects like Agreement, Moral, Nuance, Thoughtfulness and even trustworthiness.<\/strong> <\/p>\n\n\n\n<p>This shows that LLMs possess a degree of ethical expertise, with the capability to articulate moral judgments in a manner that resonates positively with people.<\/p>\n\n\n\n<p>The first study has shown that ChatGPT can explain their moral judgements better than an average human but can it surpass an expert ethicist? <\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Study 2: GPT-4o vs Humans<\/strong><\/h3>\n\n\n\n<p>The second study was a test between GPT-4o and The Ethicist, a popular column in The New York Times. <\/p>\n\n\n\n<p>The advice column writer Kwame Anthony Appiah is widely regarded for his clear and insightful moral reasoning. He is a philosopher at New York University and has written several books on ethics. Given his expertise in both theoretical and practical moral reasoning, using The Ethicist as a comparison to gauge expertise in LLMs seems right.<\/p>\n\n\n\n<p>For the second study, 900 participants were recruited. The test was conducted the same way the first study was done. They were asked to rate 50 moral explanations on a scale of 1 to 7 and give their opinion on the advice based on different qualities.<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><img decoding=\"async\" width=\"719\" height=\"673\" src=\"https:\/\/favtutor.com\/articles\/wp-content\/uploads\/2024\/08\/image1-2.png\" alt=\"GPT-4o vs The Ethicist's Advice\" class=\"wp-image-6179\"\/><\/figure>\n<\/div>\n\n\n<p>The results over here might be more shocking than the first. The AI-generated content was rated as more morally correct, trustworthy, thoughtful, and accurate than the advice given by an expert advisor in providing advice.<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><img decoding=\"async\" width=\"787\" height=\"811\" src=\"https:\/\/favtutor.com\/articles\/wp-content\/uploads\/2024\/08\/image3-1.png\" alt=\"\" class=\"wp-image-6180\" srcset=\"https:\/\/favtutor.com\/articles\/wp-content\/uploads\/2024\/08\/image3-1.png 787w, https:\/\/favtutor.com\/articles\/wp-content\/uploads\/2024\/08\/image3-1-768x791.png 768w, https:\/\/favtutor.com\/articles\/wp-content\/uploads\/2024\/08\/image3-1-750x773.png 750w\" sizes=\"(max-width: 787px) 100vw, 787px\" \/><\/figure>\n<\/div>\n\n\n<p><strong>The paper says the reason for this is that ChatGPT uses more positive words than the ethicist. Words like \u201ccan\u201d, \u201cemotional\u201d , \u201csupport\u201d , \u201cwellbeing\u201d and \u201cfamily\u201d have been used well by the LLM. <\/strong><\/p>\n\n\n\n<p>This shows that the latest GPT model, GPT-4o, provides better advice that people prefer over that of The New York Times advice column The Ethicist. <\/p>\n\n\n\n<p>In somewhat similar research, when humans are in a debate against an LLM, <a href=\"https:\/\/favtutor.com\/articles\/personalized-llm-gpt-4-more-persuasive-study\/\">the personalized LLM has 81.7% more influencing power over its opponent<\/a>.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Conclusion<\/strong><\/h2>\n\n\n\n<p>Overall, this study suggests that LLMs have achieved ethical expertise in the realm of providing guidance. The research suggests a promising future where AI can be used to provide guidance in various fields and help humans while making crucial decisions. <\/p>\n","protected":false},"excerpt":{"rendered":"<p>A new study finds that ChatGPTo outperforms human experts in giving better moral explanations in terms of accuracy and trustworthiness.<\/p>\n","protected":false},"author":29,"featured_media":6198,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"jnews-multi-image_gallery":[],"jnews_single_post":null,"jnews_primary_category":{"id":"","hide":""},"footnotes":""},"categories":[57],"tags":[56,61,258,60],"class_list":["post-6177","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai","tag-ai","tag-chatgpt","tag-gpt-4o","tag-openai"],"_links":{"self":[{"href":"https:\/\/favtutor.com\/articles\/wp-json\/wp\/v2\/posts\/6177","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/favtutor.com\/articles\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/favtutor.com\/articles\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/favtutor.com\/articles\/wp-json\/wp\/v2\/users\/29"}],"replies":[{"embeddable":true,"href":"https:\/\/favtutor.com\/articles\/wp-json\/wp\/v2\/comments?post=6177"}],"version-history":[{"count":2,"href":"https:\/\/favtutor.com\/articles\/wp-json\/wp\/v2\/posts\/6177\/revisions"}],"predecessor-version":[{"id":6182,"href":"https:\/\/favtutor.com\/articles\/wp-json\/wp\/v2\/posts\/6177\/revisions\/6182"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/favtutor.com\/articles\/wp-json\/wp\/v2\/media\/6198"}],"wp:attachment":[{"href":"https:\/\/favtutor.com\/articles\/wp-json\/wp\/v2\/media?parent=6177"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/favtutor.com\/articles\/wp-json\/wp\/v2\/categories?post=6177"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/favtutor.com\/articles\/wp-json\/wp\/v2\/tags?post=6177"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}