Closing Keynote: What Could Possibly Go Wrong? Behind-the-Scenes of AI Safety in Chatbots and Multimodal Language Models

kaylal — Wed, 21 May 2025 00:57:35 +0000

Closing Keynote: What Could Possibly Go Wrong? Behind-the-Scenes of AI Safety in Chatbots and Multimodal Language Models kaylal Tue, 05/20/2025 - 17:57

As AI tools like ChatGPT and Gemini are becoming more integrated into our workflows, an important question emerges: Can they be trusted to behave safely and predictably? This talk explores that question by sharing insights from recent research, including our own, on how AI models behave when things do not go as planned. Using real-world examples, we will show how seemingly safe inputs, such as a normal-looking image or a cleverly worded prompt, can produce unexpected and even harmful outputs. These failures can occur even in models that are labeled as aligned or safety-trained. While highlighting how these systems remain vulnerable to both simple and carefully designed jailbreak attacks, the talk will also present defense strategies. These include methods for removing harmful behaviors from model parameters, as well as practical and lightweight techniques, especially relevant for IT teams managing or evaluating AI systems across the UC system.

Yue Dong

Assistant Professor at UC Riverside

Yue Dong (yuedong.us) is an Assistant Professor in the Department of Computer Science and Engineering at the University of California, Riverside. Her research focuses on natural language processing and machine learning, with a particular emphasis on trustworthy AI and the safety of large language models (LLMs). She is recognized for her work on red teaming vision-language models, which won a Best Paper Award at SoCal NLP 2024 and was spotlighted at ICLR. Dr. Dong has authored over 30 peer-reviewed papers in top-tier venues including ACL, EMNLP, ICML, ICLR, AAAI, ICRA, and CIKM. She co-led a widely attended ACL 2024 tutorial on LLM safety and contributes actively to the research community. She has served as Senior Area Chair for ACL 2025, NAACL 2025 & 2024, EMNLP 2025 & 2024, and IJCNLP-AACL 2023, and as Area Chair for ICLR 2025, ACL 2024 & 2023, and EMNLP 2022 & 2023. She also co-organizes workshops and tutorials on summarization and efficient LLMs at EMNLP, NAACL, and NeurIPS (2021–2024).

Session Format

Keynote

Session Status

Accepted

June 27, 2025 @ 9:45 am - June 27, 2025 @ 10:30 am

EH A&B

Opening Keynote: Navigating the Student Experience in the AI Era

kaylal — Wed, 21 May 2025 00:52:40 +0000

Opening Keynote: Navigating the Student Experience in the AI Era kaylal Tue, 05/20/2025 - 17:52

Students today turn to generative AI not just for homework help, but as a study partner, a brainstorming collaborator, and a patient tutor for the questions they’re too embarrassed to ask in class. Based on our user research, this rapid adoption is driven by a desire for efficiency and a deep-seated fear of falling behind their AI-equipped peers.

This keynote will pull back the curtain on how students are truly using AI, exploring their workflows and their motivations. I'll share how we at Google are building Gemini to be a responsible and powerful partner in this journey and how we are creating immersive, interactive experiences grounded in learning science, empowering individuals to follow their curiosity, build transformative knowledge, and thrive in a changing world.

Carol Walport

Senior Product Manager at Google

Carol Walport is an Education Product Lead at Google DeepMind, where she works to build better learning experiences for students who use Gemini. Her work involves improving the quality of Gemini’s responses to student queries and building new features to better support students throughout their academic journey. Before joining Gemini, Carol led the podcast experience on YouTube and YouTube Music and launched telehealth video appointments at Zocdoc. Outside of work, she has co-produced 5 Broadway shows and invested in over 30 productions globally, including Operation Mincemeat, Suffs, and Six. She lives with her husband and her two wonderful children in New York City.

Session Format

Keynote

Session Status

Accepted

June 26, 2025 @ 9:45 am - June 26, 2025 @ 10:30 am

EH A&B