ABSTRACT
Generative ML models present a novel opportunity for a wider group of societal members to engage with AI, imagine new use cases, and applications with an increasing ability to disseminate the outcomes of such endeavors to larger audiences. However, owing to the novelty and despite best intentions, inadvertent outcomes might accrue leading to harms, especially to marginalized groups in society. As this field of Human AI Interaction advances, academic/industry researchers, and industry practitioners have an opportunity to brainstorm how to best utilize this new technology. Our workshop is aimed at such practitioners and researchers at the intersection of AI and HCI who are interested in collaboratively identifying challenges, and solutions to create safer outcomes with Generative ML models.
- Saleema Amershi, Max Chickering, Steven M Drucker, Bongshin Lee, Patrice Simard, and Jina Suh. 2015. Modeltracker: Redesigning performance analysis tools for machine learning. In Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems. 337–346.Google ScholarDigital Library
- Zinat Ara and Sungsoo Ray Hong. 2023. Exploring Design Space of Collaborative Career-Seeking Experience for People on Autism Spectrum. (2023).Google Scholar
- Amanda Baughan, Ashwin Rajadesingan, Alexis Hiniker, Paul Resnick, and Amy Bruckman. 2022. SIG on Designing for Constructive Conflict. In Extended Abstracts of the 2022 CHI Conference on Human Factors in Computing Systems(CHI EA ’22). Association for Computing Machinery, New York, NY, USA, 1–2.Google Scholar
- Minsuk Choi, Cheonbok Park, Soyoung Yang, Yonggyu Kim, Jaegul Choo, and Sungsoo Ray Hong. 2019. Aila: Attentive interactive labeling assistant for document classification through attention-based deep neural networks. In Proceedings of the 2019 CHI conference on human factors in computing systems. 1–12.Google ScholarDigital Library
- Alexandra Chouldechova and Aaron Roth. 2018. The frontiers of fairness in machine learning. arXiv preprint arXiv:1810.08810 (2018).Google Scholar
- Jerry Alan Fails and Dan R Olsen Jr. 2003. Interactive machine learning. In Proceedings of the 8th international conference on Intelligent user interfaces. 39–45.Google ScholarDigital Library
- Laura Fearnley. 2023. Norms and Causation in Artificial Morality. (2023).Google Scholar
- Yuyang Gao, Tong Sun, Rishab Bhatt, Dazhou Yu, Sungsoo Hong, and Liang Zhao. 2021. Gnes: Learning to explain graph neural networks. In 2021 IEEE International Conference on Data Mining (ICDM). IEEE, 131–140.Google ScholarCross Ref
- Yuyang Gao, Tong Steven Sun, Liang Zhao, and Sungsoo Ray Hong. 2022. Aligning eyes between humans and deep neural network through interactive attention alignment. Proceedings of the ACM on Human-Computer Interaction 6, CSCW2 (2022), 1–28.Google ScholarDigital Library
- Nitesh Goyal, Ian Kivlichan, Rachel Rosen, and Lucy Vasserman. 2022. Is Your Toxicity My Toxicity? Exploring the Impact of Rater Identity on Toxicity Annotation. In Proceedings of ACM in Human Computer Interaction CSCW.Google ScholarDigital Library
- Anhong Guo, Ece Kamar, Jennifer Wortman Vaughan, Hanna Wallach, and Meredith Ringel Morris. 2020. Toward fairness in AI for people with disabilities: A research roadmap. ACM SIGACCESS Accessibility and Computing125 (2020), 1–1.Google Scholar
- Lisa Anne Hendricks, Kaylee Burns, Kate Saenko, Trevor Darrell, and Anna Rohrbach. 2018. Women also snowboard: Overcoming bias in captioning models. In Proceedings of the European Conference on Computer Vision (ECCV). 771–787.Google ScholarDigital Library
- Kenneth Holstein, Jennifer Wortman Vaughan, Hal Daumé III, Miro Dudik, and Hanna Wallach. 2019. Improving fairness in machine learning systems: What do industry practitioners need?. In Proceedings of the 2019 CHI conference on human factors in computing systems. 1–16.Google ScholarDigital Library
- Sungsoo Ray Hong, Jessica Hullman, and Enrico Bertini. 2020. Human Factors in Model Interpretability: Industry Practices, Challenges, and Needs. In Proceedings of the ACM on Human-Computer Interaction CSCW, Vol. 4. 1–26.Google ScholarDigital Library
- Douwe Kiela, Hamed Firooz, Aravind Mohan, Vedanuj Goswami, Amanpreet Singh, Pratik Ringshia, and Davide Testuggine. 2020. The hateful memes challenge: Detecting hate speech in multimodal memes. Advances in Neural Information Processing Systems 33 (2020), 2611–2624.Google Scholar
- Yubo Kou and Xinning Gui. 2021. Flag and Flaggability in Automated Moderation: The Case of Reporting Toxic Behavior in an Online Game Community. In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems (Yokohama, Japan). 1–12.Google ScholarDigital Library
- Toby Jia-Jun Li, Jingya Chen, Haijun Xia, Tom M Mitchell, and Brad A Myers. 2020. Multi-modal repairs of conversational breakdowns in task-oriented dialogs. In Proceedings of the 33rd Annual ACM Symposium on User Interface Software and Technology. 1094–1107.Google Scholar
- Neil McDonnell. 2023. The Philosophy of X in XAI. In Proceedings of the ACM IUI Workshops, Vol. 2023.Google Scholar
- Meta. 2022. BlenderBot 3: An AI Chatbot That Improves Through Conversation. Retrieved 02 23 2023 from https://about.fb.com/news/2022/08/blenderbot-ai-chatbot-improves-through-conversation/Google Scholar
- Andrew Sellars. 2016. Defining hate speech. Berkman Klein Center Research Publication2016-20 (2016), 16–48.Google ScholarCross Ref
- Sarah Tan, Julius Adebayo, Kori Inkpen, and Ece Kamar. 2018. Investigating human+ machine complementarity for recidivism predictions. CoRR abs/1808.09123 (2018).Google Scholar
- Almira Osmanovic Thunström. 2022. We Asked GPT-3 to Write an Academic Paper about Itself—Then We Tried to Get It Published. Retrieved 02 23 2023 from https://www.scientificamerican.com/article/we-asked-gpt-3-to-write-an-academic-paper-about-itself-mdash-then-we-tried-to-get-it-published/Google Scholar
- James Vincent. 2022. YouTuber trains AI bot on 4chan’s pile o’ bile with entirely predictable results. https://www.theverge.com/2022/6/8/23159465/youtuber-ai-bot-pol-gpt-4chan-yannic-kilcher-ethicsGoogle Scholar
- Dakuo Wang, Liuping Wang, Zhan Zhang, Ding Wang, Haiyi Zhu, Yvonne Gao, Xiangmin Fan, and Feng Tian. 2021. “Brilliant AI Doctor” in Rural Clinics: Challenges in AI-Powered Clinical Decision Support System Deployment. In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. 1–18.Google ScholarDigital Library
- Tris Warkentin and Josh Woodward. 2022. Join us in the AI Test Kitchen. Retrieved 02 23 2023 from https://blog.google/technology/ai/join-us-in-the-ai-test-kitchen/Google Scholar
- Yong Xie, Dakuo Wang, Pin-Yu Chen, Jinjun Xiong, Sijia Liu, and Sanmi Koyejo. 2022. A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock Prediction. NAACL (2022).Google Scholar
- Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez, and Kai-Wei Chang. 2017. Men also like shopping: Reducing gender bias amplification using corpus-level constraints. arXiv preprint arXiv:1707.09457 (2017).Google Scholar
Index Terms
- SHAI 2023: Workshop on Designing for Safety in Human-AI Interactions
Recommendations
GenAICHI 2023: Generative AI and HCI at CHI 2023
CHI EA '23: Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing SystemsThis workshop applies human centered themes to a new and powerful technology, generative artificial intelligence (AI). Unlike AI systems that produce decisions or descriptions, generative AI systems can produce new and creative content that can include ...
System Safety and Artificial Intelligence
FAccT '22: Proceedings of the 2022 ACM Conference on Fairness, Accountability, and TransparencyThis article formulates seven lessons for preventing harm in artificial intelligence (AI) systems based on insights from the field of system safety for software-based automation in safety-critical domains. New applications of AI across societal domains ...
Create Effective and Responsible AI User Experiences with The Human-AI Experience (HAX) Toolkit
CHI EA '23: Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing SystemsThe HAX Toolkit (https://aka.ms/haxtoolkit) is a set of collaborative tools that helps teams working on user-facing AI plan, create, and evaluate human-AI user experiences. This course will help AI practitioners, human-AI interaction researchers, ...
Comments