{"id":28625,"date":"2022-03-04T06:00:00","date_gmt":"2022-03-04T14:00:00","guid":{"rendered":"https:\/\/insidebigdata.com\/?p=28625"},"modified":"2023-06-23T12:42:48","modified_gmt":"2023-06-23T19:42:48","slug":"research-highlights-using-theory-of-mind-to-improve-human-trust-in-artificial-intelligence","status":"publish","type":"post","link":"https:\/\/insidebigdata.com\/2022\/03\/04\/research-highlights-using-theory-of-mind-to-improve-human-trust-in-artificial-intelligence\/","title":{"rendered":"Research Highlights: Using Theory of Mind to improve Human Trust in Artificial Intelligence"},"content":{"rendered":"
\n
\"\"<\/figure><\/div>\n\n\n

Artificial Intelligence (AI) systems are threaded throughout modern society, informing us in low-risk interactions such as movie recommendations and chatbots to high-risk environments like medical diagnosis, self-driving cars, drones, and military operations. But is remains a significant challenge to develop human trust in these systems, particularly because the systems themselves cannot explain in a way graspable to humans how a recommendation or decision was reached. This lack of trust can become problematic in critical situations involving finances or healthcare where AI decisions can have life-altering consequences.<\/p>\n\n\n\n

To address this issue, eXplainable Artificial Intelligence (XAI) has become an active research area both for scientists and industry. XAI develops models using explanations that aim to shed light on the underlying mechanisms of AI systems, thus bringing transparency to the process. Results become more capable of being interpreted by both experts and non-expert end users alike.<\/p>\n\n\n\n

New research by a team of UCLA<\/a> scientists is focused on boosting human trust in these increasingly common systems by greatly improving upon XAI. Their study was recently published in the journal iScience – “CX-ToM Counterfactual explanations with theory-of-mind for enhancing human trust in image recognition models<\/a>.”<\/p>\n\n\n\n

\n

\u201cHumans can easily be overwhelmed with too many or too detailed explanations. Our interactive communication process helps machine in understanding the human user and identify user-specific content for explanation,\u201d says Song-Chun Zhu, the project\u2019s principal investigator and a professor of statistics and computer science at UCLA.<\/p>\n<\/blockquote>\n\n\n

\n
\"\"<\/figure><\/div>\n\n\n

Zhu and his team at UCLA set out to improve existing XAI models and to pose the explanation generation as an iterative process of communication between the human and the machine. They use the Theory of Mind (ToM) framework to drive this communication dialog. ToM helps in explicitly tracking three important aspects at each dialog turn: (a) human\u2019s intention (or curiosity); (b) human\u2019s understanding of the machine; and (c) machine\u2019s understanding of the human user.<\/p>\n\n\n\n

\n

\u201cIn our framework, we let the machine and the user solve a collaborative task, but the machine’s mind and the human user’s mind only have a partial knowledge of the environment. Hence, the machine and user need to communicate with each other in a dialog, using their partial knowledge, otherwise they would not be able to optimally solve the collaborative task,\u201d said Arjun Reddy Akula<\/a>, the UCLA Ph.D. student who led this work for Prof. Zhu\u2019s group. \u201cOur work will make it easier for non-expert AI human users to operate, understand and improve human trust in AI-based systems. We believe our interactive ToM based framework provides a new way of thinking at designing XAI solutions.”<\/p>\n<\/blockquote>\n\n\n\n

The group\u2019s latest development is the culmination of research in their UCLA laboratory over five years.<\/p>\n\n\n\n

Sign up for the free insideBIGDATA newsletter<\/a>.<\/em><\/p>\n\n\n\n

Join us on Twitter: @InsideBigData1 \u2013 https:\/\/twitter.com\/InsideBigData1<\/a><\/em><\/p>\n","protected":false},"excerpt":{"rendered":"

eXplainable Artificial Intelligence (XAI) has become an active research area both for scientists and industry. XAI develops models using explanations that aim to shed light on the underlying mechanisms of AI systems, thus bringing transparency to the process. Results become more capable of being interpreted by both experts and non-expert end users alike. New research by a team of UCLA scientists is focused on boosting human trust in these increasingly common systems by greatly improving upon XAI. Their study was recently published in the journal iScience.<\/p>\n","protected":false},"author":10513,"featured_media":28628,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"jetpack_post_was_ever_published":false,"footnotes":""},"categories":[184,526,87,180,56,84,1303,1],"tags":[437,324,264,898,95,973],"acf":[],"yoast_head":"\nResearch Highlights: Using Theory of Mind to improve Human Trust in Artificial Intelligence - insideBIGDATA<\/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:\/\/insidebigdata.com\/2022\/03\/04\/research-highlights-using-theory-of-mind-to-improve-human-trust-in-artificial-intelligence\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Research Highlights: Using Theory of Mind to improve Human Trust in Artificial Intelligence - insideBIGDATA\" \/>\n<meta property=\"og:description\" content=\"eXplainable Artificial Intelligence (XAI) has become an active research area both for scientists and industry. XAI develops models using explanations that aim to shed light on the underlying mechanisms of AI systems, thus bringing transparency to the process. Results become more capable of being interpreted by both experts and non-expert end users alike. New research by a team of UCLA scientists is focused on boosting human trust in these increasingly common systems by greatly improving upon XAI. Their study was recently published in the journal iScience.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/insidebigdata.com\/2022\/03\/04\/research-highlights-using-theory-of-mind-to-improve-human-trust-in-artificial-intelligence\/\" \/>\n<meta property=\"og:site_name\" content=\"insideBIGDATA\" \/>\n<meta property=\"article:publisher\" content=\"http:\/\/www.facebook.com\/insidebigdata\" \/>\n<meta property=\"article:published_time\" content=\"2022-03-04T14:00:00+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-06-23T19:42:48+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/insidebigdata.com\/wp-content\/uploads\/2022\/03\/UCLACS_theory_of_mind_logo.png\" \/>\n\t<meta property=\"og:image:width\" content=\"248\" \/>\n\t<meta property=\"og:image:height\" content=\"59\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Editorial Team\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@insideBigData\" \/>\n<meta name=\"twitter:site\" content=\"@insideBigData\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Editorial Team\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/insidebigdata.com\/2022\/03\/04\/research-highlights-using-theory-of-mind-to-improve-human-trust-in-artificial-intelligence\/\",\"url\":\"https:\/\/insidebigdata.com\/2022\/03\/04\/research-highlights-using-theory-of-mind-to-improve-human-trust-in-artificial-intelligence\/\",\"name\":\"Research Highlights: Using Theory of Mind to improve Human Trust in Artificial Intelligence - insideBIGDATA\",\"isPartOf\":{\"@id\":\"https:\/\/insidebigdata.com\/#website\"},\"datePublished\":\"2022-03-04T14:00:00+00:00\",\"dateModified\":\"2023-06-23T19:42:48+00:00\",\"author\":{\"@id\":\"https:\/\/insidebigdata.com\/#\/schema\/person\/2949e412c144601cdbcc803bd234e1b9\"},\"breadcrumb\":{\"@id\":\"https:\/\/insidebigdata.com\/2022\/03\/04\/research-highlights-using-theory-of-mind-to-improve-human-trust-in-artificial-intelligence\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/insidebigdata.com\/2022\/03\/04\/research-highlights-using-theory-of-mind-to-improve-human-trust-in-artificial-intelligence\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/insidebigdata.com\/2022\/03\/04\/research-highlights-using-theory-of-mind-to-improve-human-trust-in-artificial-intelligence\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/insidebigdata.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Research Highlights: Using Theory of Mind to improve Human Trust in Artificial Intelligence\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/insidebigdata.com\/#website\",\"url\":\"https:\/\/insidebigdata.com\/\",\"name\":\"insideBIGDATA\",\"description\":\"Your Source for AI, Data Science, Deep Learning & Machine Learning Strategies\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/insidebigdata.com\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/insidebigdata.com\/#\/schema\/person\/2949e412c144601cdbcc803bd234e1b9\",\"name\":\"Editorial Team\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/insidebigdata.com\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/e137ce7ea40e38bd4d25bb7860cfe3e4?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/e137ce7ea40e38bd4d25bb7860cfe3e4?s=96&d=mm&r=g\",\"caption\":\"Editorial Team\"},\"sameAs\":[\"http:\/\/www.insidebigdata.com\"],\"url\":\"https:\/\/insidebigdata.com\/author\/editorial\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Research Highlights: Using Theory of Mind to improve Human Trust in Artificial Intelligence - insideBIGDATA","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:\/\/insidebigdata.com\/2022\/03\/04\/research-highlights-using-theory-of-mind-to-improve-human-trust-in-artificial-intelligence\/","og_locale":"en_US","og_type":"article","og_title":"Research Highlights: Using Theory of Mind to improve Human Trust in Artificial Intelligence - insideBIGDATA","og_description":"eXplainable Artificial Intelligence (XAI) has become an active research area both for scientists and industry. XAI develops models using explanations that aim to shed light on the underlying mechanisms of AI systems, thus bringing transparency to the process. Results become more capable of being interpreted by both experts and non-expert end users alike. New research by a team of UCLA scientists is focused on boosting human trust in these increasingly common systems by greatly improving upon XAI. Their study was recently published in the journal iScience.","og_url":"https:\/\/insidebigdata.com\/2022\/03\/04\/research-highlights-using-theory-of-mind-to-improve-human-trust-in-artificial-intelligence\/","og_site_name":"insideBIGDATA","article_publisher":"http:\/\/www.facebook.com\/insidebigdata","article_published_time":"2022-03-04T14:00:00+00:00","article_modified_time":"2023-06-23T19:42:48+00:00","og_image":[{"width":248,"height":59,"url":"https:\/\/insidebigdata.com\/wp-content\/uploads\/2022\/03\/UCLACS_theory_of_mind_logo.png","type":"image\/png"}],"author":"Editorial Team","twitter_card":"summary_large_image","twitter_creator":"@insideBigData","twitter_site":"@insideBigData","twitter_misc":{"Written by":"Editorial Team","Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/insidebigdata.com\/2022\/03\/04\/research-highlights-using-theory-of-mind-to-improve-human-trust-in-artificial-intelligence\/","url":"https:\/\/insidebigdata.com\/2022\/03\/04\/research-highlights-using-theory-of-mind-to-improve-human-trust-in-artificial-intelligence\/","name":"Research Highlights: Using Theory of Mind to improve Human Trust in Artificial Intelligence - insideBIGDATA","isPartOf":{"@id":"https:\/\/insidebigdata.com\/#website"},"datePublished":"2022-03-04T14:00:00+00:00","dateModified":"2023-06-23T19:42:48+00:00","author":{"@id":"https:\/\/insidebigdata.com\/#\/schema\/person\/2949e412c144601cdbcc803bd234e1b9"},"breadcrumb":{"@id":"https:\/\/insidebigdata.com\/2022\/03\/04\/research-highlights-using-theory-of-mind-to-improve-human-trust-in-artificial-intelligence\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/insidebigdata.com\/2022\/03\/04\/research-highlights-using-theory-of-mind-to-improve-human-trust-in-artificial-intelligence\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/insidebigdata.com\/2022\/03\/04\/research-highlights-using-theory-of-mind-to-improve-human-trust-in-artificial-intelligence\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/insidebigdata.com\/"},{"@type":"ListItem","position":2,"name":"Research Highlights: Using Theory of Mind to improve Human Trust in Artificial Intelligence"}]},{"@type":"WebSite","@id":"https:\/\/insidebigdata.com\/#website","url":"https:\/\/insidebigdata.com\/","name":"insideBIGDATA","description":"Your Source for AI, Data Science, Deep Learning & Machine Learning Strategies","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/insidebigdata.com\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/insidebigdata.com\/#\/schema\/person\/2949e412c144601cdbcc803bd234e1b9","name":"Editorial Team","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/insidebigdata.com\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/e137ce7ea40e38bd4d25bb7860cfe3e4?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/e137ce7ea40e38bd4d25bb7860cfe3e4?s=96&d=mm&r=g","caption":"Editorial Team"},"sameAs":["http:\/\/www.insidebigdata.com"],"url":"https:\/\/insidebigdata.com\/author\/editorial\/"}]}},"jetpack_featured_media_url":"https:\/\/insidebigdata.com\/wp-content\/uploads\/2022\/03\/UCLACS_theory_of_mind_logo.png","jetpack_shortlink":"https:\/\/wp.me\/p9eA3j-7rH","jetpack-related-posts":[{"id":17174,"url":"https:\/\/insidebigdata.com\/2017\/02\/14\/dr-eng-lim-goh-new-trends-big-data-deep-learning-artificial-intelligence\/","url_meta":{"origin":28625,"position":0},"title":"Dr. Eng Lim Goh on New Trends in Big Data and Deep Learning for Artificial Intelligence","date":"February 14, 2017","format":false,"excerpt":"In this video from SC16, Dr. Eng Lim Goh from HPE\/SGI discusses new trends in HPC Energy Efficiency and Deep Learning for Artificial Intelligence. \"Recently acquired by Hewlett Packard Enterprise, SGI is a trusted leader in technical computing with a focus on helping customers solve their most demanding business and\u2026","rel":"","context":"In "Academic"","img":{"alt_text":"","src":"https:\/\/i0.wp.com\/insidebigdata.com\/wp-content\/uploads\/2017\/02\/goh.jpg?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":22879,"url":"https:\/\/insidebigdata.com\/2019\/07\/04\/infographic-can-ai-think-ethically\/","url_meta":{"origin":28625,"position":1},"title":"Infographic: Can AI Think Ethically?","date":"July 4, 2019","format":false,"excerpt":"Cities across the world are using \u2014 or banning because of concerns about bias \u2014 facial recognition technology, but is it possible for artificial intelligence to think ethically? We've written about the ethics of AI extensively here on insideBIGDATA. To further the conversation, the infographic below developed by our friends\u2026","rel":"","context":"In "AI Deep Learning"","img":{"alt_text":"","src":"https:\/\/i0.wp.com\/insidebigdata.com\/wp-content\/uploads\/2019\/06\/NowSourcing_infographic.png?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":19603,"url":"https:\/\/insidebigdata.com\/2017\/12\/16\/impressive-technologies-driving-artificial-intelligence\/","url_meta":{"origin":28625,"position":2},"title":"Impressive Technologies Driving the Artificial Intelligence","date":"December 16, 2017","format":false,"excerpt":"In this contributed article, Sharmistha Sarkar of India based Progressive Markets, highlights a handful of compelling technology advancements that are helping to drive the evolution of artificial intelligence. Industry is expected to grow at a CAGR of 46.5% from 2017 to 2025. The market is growing fast due to improved\u2026","rel":"","context":"In "AI Deep Learning"","img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":22635,"url":"https:\/\/insidebigdata.com\/2019\/05\/16\/how-the-eu-is-mastering-the-challenge-of-trustworthy-artificial-intelligence\/","url_meta":{"origin":28625,"position":3},"title":"How the EU is Mastering the Challenge of Trustworthy Artificial Intelligence","date":"May 16, 2019","format":false,"excerpt":"From treating chronic diseases and reducing fatality rates in traffic accidents, to fighting climate change and anticipating cybersecurity threats, Artificial Intelligence (AI) is no longer considered a futuristic construct - it is already a reality and is helping humanity solve pressing global challenges. It significantly improves peoples\u2019 lives, helps with\u2026","rel":"","context":"In "AI Deep Learning"","img":{"alt_text":"","src":"https:\/\/i0.wp.com\/insidebigdata.com\/wp-content\/uploads\/2019\/05\/Artificial_intelligence_SHUTTERSTOCK.jpg?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":14743,"url":"https:\/\/insidebigdata.com\/2016\/03\/31\/rage-frameworks-pioneers-contextual-deep-learning-with-its-artificial-intelligence-platform\/","url_meta":{"origin":28625,"position":4},"title":"Rage Frameworks Pioneers Contextual Deep Learning with its Artificial Intelligence Platform","date":"March 31, 2016","format":false,"excerpt":"Rage Frameworks, a provider of knowledge-based automation technology and services, announced new deployments of its traceable \u201cdeep learning\u201d technology known as Rage AI\u2122 across several global financial services, consumer products and manufacturing firms.","rel":"","context":"In "Featured"","img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":25684,"url":"https:\/\/insidebigdata.com\/2021\/02\/25\/ai-in-cybersecurity-six-considerations-for-2021\/","url_meta":{"origin":28625,"position":5},"title":"AI in Cybersecurity: Six Considerations for 2021","date":"February 25, 2021","format":false,"excerpt":"In this contributed article, Erick Galinkin, Principal Artificial Intelligence Researcher at Rapid7, suggests that for businesses looking to implement more AI into their security stack in 2021, it\u2019s important to follow these six steps to ensure the effective use of AI \u2013 without compromising security anywhere else down the line.","rel":"","context":"In "AI Deep Learning"","img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]}],"_links":{"self":[{"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/posts\/28625"}],"collection":[{"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/users\/10513"}],"replies":[{"embeddable":true,"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/comments?post=28625"}],"version-history":[{"count":0,"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/posts\/28625\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/media\/28628"}],"wp:attachment":[{"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/media?parent=28625"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/categories?post=28625"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/tags?post=28625"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}