<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=Windows-1252">
<style type="text/css" style="display:none;"> P {margin-top:0;margin-bottom:0;} </style>
</head>
<body dir="ltr">
<div class="elementToProof" style="font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<b><i>Department of Computer Science Seminar</i></b></div>
<div style="direction: ltr; font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<b><br>
</b></div>
<div style="direction: ltr; font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<b>Bo Li</b></div>
<ul style="direction: ltr; text-align: left; margin: 0px; padding-left: 0px; list-style-position: outside; list-style-type: none;">
<li style="font-family: Arial, Helvetica, sans-serif; font-size: 11pt; font-weight: 300; color: rgb(0, 0, 0); direction: ltr;">
<span style="font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);"><b>Neubauer Associate Professor of Computer Science, Data Science</b></span></li></ul>
<div style="direction: ltr; font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<b>University of Chicago</b></div>
<div style="direction: ltr; font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<b><br>
</b></div>
<div style="direction: ltr; font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<b><br>
</b></div>
<div style="direction: ltr; font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<b>Tuesday, May 14th</b></div>
<div style="direction: ltr; font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<b>12:30pm - 2:00pm</b></div>
<div style="direction: ltr; font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<b>In person: John Crerar Library 298</b></div>
<div style="direction: ltr; font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="direction: ltr; font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<b>Zoom information</b>: <a href="https://uchi-jcl.github.io/seminar" id="OWA0a22550d-8947-7403-f57b-48a758e03479" class="x_OWAAutoLink" title="https://uchi-jcl.github.io/seminar" data-auth="NotApplicable" data-loopstyle="linkonly">
https://uchi-jcl.github.io/seminar</a></div>
<div style="direction: ltr; font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="direction: ltr; font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<b>Title: Risk Assessment, Safety Alignment, and Guardrails for Generative Models<br>
</b><br>
<b>Abstract</b>:<br>
Large language models (LLMs) have garnered widespread attention due to their impressive performance across a range of applications. However, our understanding of the trustworthiness and risks of these models remains limited. The temptation to deploy proficient
foundation models in sensitive domains like healthcare and finance, where errors carry significant consequences, underscores the need for rigorous safety evaluations, enhancement, and guarantees. Recognizing the urgent need for developing safe and beneficial
AI, our recent research seeks to design a unified platform to evaluate the safety of LLMs from diverse perspectives such as toxicity, stereotype bias, adversarial robustness, OOD robustness, ethics, privacy, and fairness; enhance LLM safety through knowledge
integration; and provide safety guardrail and certifications. In this talk, I will first outline our foundational principles for safety evaluation, detail our red teaming tactics, and share insights gleaned from applying our Decoding Trust platform to different
models, such as proprietary and open-source models, as well as compressed models. Further, I will delve into our methods for enhancing model safety, such as hallucination mitigation. I will also explain how knowledge integration helps align models and prove
that the RAG framework achieves provably lower conformal generation risks compared to vanilla LLMs. Finally, I will briefly discuss our robust guardrail framework for risk mitigation in practice.<br>
<br>
<b>Bio</b>:<br>
Dr. Bo Li is the Neubauer Associate Professor in the Department of Computer Science at the University of Chicago. She is the recipient of the IJCAI Computers and Thought Award, Alfred P. Sloan Research Fellowship, IEEE AI’s 10 to Watch, NSF CAREER Award, MIT
Technology Review TR-35 Award, Dean’s Award for Excellence in Research, C.W. Gear Outstanding Faculty Award, Intel Rising Star Award, Symantec Research Labs Fellowship, Rising Star Award, Research Awards from Tech companies such as Amazon, Meta, Google, Intel,
IBM, and eBay, and best paper awards at several top machine learning and security conferences. Her research focuses on both theoretical and practical aspects of trustworthy machine learning, which is at the intersection of machine learning, security, privacy,
and game theory. She has designed several scalable frameworks for certifiably robust learning and privacy-preserving data publishing. Her work has been featured by several major publications and media outlets, including Nature, Wired, Fortune, and New York
Times.</div>
<div style="direction: ltr; font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="direction: ltr; font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
Her website is: <a href="https://aisecure.github.io" id="OWAf84ef732-82d3-673b-01bf-65cfc8bf86a4" class="OWAAutoLink" title="https://aisecure.github.io" data-auth="NotApplicable" data-loopstyle="linkonly">
https://aisecure.github.io</a></div>
<div style="direction: ltr; font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="direction: ltr; font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="direction: ltr; font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="direction: ltr; font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="direction: ltr; font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="direction: ltr; font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="direction: ltr; font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<br>
</div>
<div id="x_Signature">
<div style="font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<b>Abigail Santana</b></div>
<div style="font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
Business Assistant - Computer Science</div>
<div style="font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
The University of Chicago</div>
<div style="font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
5730 S Ellis Ave, JCL 212</div>
<div style="font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
Chicago, IL 60637</div>
<div style="font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(12, 100, 192);">
<u>asantana01@uchicago.edu</u></div>
<div style="font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
Office: 773-834-2750</div>
<div style="font-family: Arial, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<br>
</div>
</div>
</body>
</html>