{"id":911151,"date":"2023-01-12T09:00:00","date_gmt":"2023-01-12T17:00:00","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?p=911151"},"modified":"2023-01-13T12:11:17","modified_gmt":"2023-01-13T20:11:17","slug":"advancing-human-centered-ai-updates-on-responsible-ai-research","status":"publish","type":"post","link":"https:\/\/www.microsoft.com\/en-us\/research\/blog\/advancing-human-centered-ai-updates-on-responsible-ai-research\/","title":{"rendered":"Advancing human-centered AI: Updates on responsible AI research"},"content":{"rendered":"\n

Editor\u2019s note: <\/strong>All papers referenced here represent collaborations throughout Microsoft and across academia and industry that include authors who contribute to Aether, the Microsoft internal advisory body for AI Ethics and Effects in Engineering and Research.<\/em><\/p>\n\n\n\n

\n\n\n\n
\"illustration<\/figure>\n\n\n\n
\n\t
\n\t\t
\n\t\t\t\t\t\t\t\n\t\t\t\t\t\"Video\t\t\t\t<\/a>\n\t\t\t\t\t\t\tVideo<\/span>\n\t\t\tA human-centered approach to AI<\/span> <\/span><\/a>\t\t\t\t\t\t\t

Learn how considering potential benefits and harms to people and society helps create better AI in the keynote \u201cChallenges and opportunities in responsible AI\u201d (2022 ACM SIGIR Conference on Human Information Interaction and Retrieval).<\/p>\n\t\t\t\t\t<\/div>\n\t<\/article>\n<\/div>\n\n\n\n

Artificial intelligence, like all tools we build, is an expression of human creativity. As with all creative expression, AI manifests the perspectives and values of its creators. A stance that encourages reflexivity among AI practitioners is a step toward ensuring that AI systems are human-centered<\/em>, developed and deployed with the interests and well-being of individuals and society front and center. This is the focus of research scientists and engineers affiliated with Aether<\/a>, the advisory body for Microsoft leadership on AI ethics and effects. Central to Aether\u2019s work is the question of who we\u2019re creating AI for\u2014and whether we\u2019re creating AI to solve real problems with responsible solutions. With AI capabilities accelerating, our researchers work to understand the sociotechnical implications and find ways to help on-the-ground practitioners envision and realize these capabilities in line with Microsoft AI principles<\/a>.<\/p>\n\n\n\n

The following is a glimpse into the past year\u2019s research for advancing responsible AI with authors from Aether. Throughout this work are repeated calls for reflexivity in AI practitioners\u2019 processes\u2014that is, self-reflection to help us achieve clarity about who we\u2019re developing AI systems for, who benefits, and who may potentially be harmed\u2014and for tools that help practitioners with the hard work of uncovering assumptions that may hinder the potential of human-centered AI. The research discussed here also explores critical components of responsible AI, such as being transparent about technology limitations, honoring the values of the people using the technology, enabling human agency for optimal human-AI teamwork, improving effective interaction with AI, and developing appropriate evaluation and risk-mitigation techniques for multimodal machine learning (ML) models.<\/p>\n\n\n\n

Considering who AI systems are for<\/h2>\n\n\n\n

The need to cultivate broader perspectives and, for society\u2019s benefit, reflect on why and for whom we\u2019re creating AI is not only the responsibility of AI development teams but also of the AI research community. In the paper \u201cREAL ML: Recognizing, Exploring, and Articulating Limitations of Machine Learning Research<\/a>,\u201d <\/em>the authors point out that machine learning publishing often exhibits a bias toward emphasizing exciting progress, which tends to propagate misleading expectations about AI. They urge reflexivity on the limitations of ML research to promote transparency about findings\u2019 generalizability and potential impact on society\u2014ultimately, an exercise in reflecting on who we\u2019re creating AI for. The paper offers a set of guided activities designed to help articulate research limitations (opens in new tab)<\/span><\/a>, encouraging the machine learning research community toward a standard practice of transparency about the scope and impact of their work. <\/p>\n\n\n\n

\"Graphic<\/a><\/figure>
\n

Walk through REAL ML\u2019s instructional guide and worksheet that help researchers with defining the limitations of their research and identifying societal implications these limitations may have in the practical use of their work.<\/p>\n\n\n\n

\n
Explore REAL ML<\/a><\/div>\n<\/div>\n<\/div><\/div>\n\n\n\n

Despite many organizations formulating principles to guide the responsible development and deployment of AI, a recent survey highlights that there\u2019s a gap between the values prioritized by AI practitioners and those of the general public<\/a>. The survey, which included a representative sample of the US population, found AI practitioners often gave less weight than the general public to values associated with responsible AI. This raises the question of whose values should inform AI systems and shifts attention toward considering the values of the people we\u2019re designing for, aiming for AI systems that are better aligned with people\u2019s needs.<\/p>\n\n\n\n

Related papers<\/h4>\n\n\n\n