<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=koi8-r">
<meta name="Generator" content="Microsoft Word 15 (filtered medium)">
<style><!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Aptos;}
/* Style Definitions */
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:#467886;
text-decoration:underline;}
span.EmailStyle19
{mso-style-type:personal-compose;}
.MsoChpDefault
{mso-style-type:export-only;
font-size:10.0pt;
mso-ligatures:none;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
{page:WordSection1;}
--></style>
</head>
<body lang="EN-US" link="#467886" vlink="#96607D" style="word-wrap:break-word">
<div class="WordSection1">
<p>CV, title, and abstract attached.<o:p></o:p></p>
<p><b>Towards Trustworthy AI-Enabled Systems: Systematic Test & Evaluation and Future Directions<o:p></o:p></b></p>
<p>Artificial Intelligence-enabled systems (AI systems) are increasingly deployed across domains, including high-stakes, safety-critical domains. Yet a fundamental gap persists: AI systems that perform well in research settings often fail catastrophically when
deployed in production. High-profile failures in medical AI and autonomous vehicles reveal the inadequacy of current evaluation practices for ensuring real-world reliability.
<o:p></o:p></p>
<p>My research at the intersection of Software Engineering and AI addresses this challenge. In the SE-for-AI direction, I develop systematic test and evaluation (T&E) methodologies to ensure AI systems work reliably in real-world conditions. My work spans the
AI systems lifecycle from model development through post-deployment with a focus on systematic T&E methods that scale across AI technologies, from deep neural networks to large language models.<o:p></o:p></p>
<p>In this talk, I will present the multifaceted challenges in the T&E of AI systems throughout their lifecycle and discuss my recent work applying combinatorial testing, a black-box testing technique, to evaluate LLM robustness. This study reveals that commercially
available LLMs exhibit inconsistent responses to multiple-choice questions based solely on option reordering, a critical concern for deployed LLMs.<o:p></o:p></p>
<p>Looking forward, I will outline my envisioned research program that explores the bidirectional relationship between software engineering and AI. In the SE4AI direction, I will discuss my vision for developing a comprehensive T&E ecosystem comprising methods,
tools, and metrics that address the multifaceted T&E challenges at every stage of the AI-enabled system’s lifecycle. In the AI4SE direction, I will share plans for leveraging AI, specifically LLMs, to augment and improve traditional software testing practices.
<o:p></o:p></p>
<p>Together, this bidirectional research vision will enable practitioners to build, deploy, and maintain AI-enabled software systems that can be trusted to operate robustly and reliably in the real world, and to successfully leverage AI to enhance software
testing practices, thereby positioning my research program to advance the field in both directions.<o:p></o:p></p>
<p>€€€€€€€€€€<br>
Join Zoom Meeting<br>
<a href="https://nam12.safelinks.protection.outlook.com/?url=https%3A%2F%2Ftamucc.zoom.us%2Fj%2F99246892329%3Fpwd%3D88fJrCJgjkin0izcE2ByQtbk1OrLEJ.1&data=05%7C02%7Ccosc-grad-students-list%40listserv.tamucc.edu%7C49e624af4bca45f67b1f08de68f4da4e%7C34cbfaf167a64781a9ca514eb2550b66%7C0%7C0%7C639063598283603990%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=Q5Zfcz09vc7JwLY47iUa7VP5JhxKwpNxHjg5BZ4uDFU%3D&reserved=0" originalsrc="https://tamucc.zoom.us/j/99246892329?pwd=88fJrCJgjkin0izcE2ByQtbk1OrLEJ.1">https://tamucc.zoom.us/j/99246892329?pwd=88fJrCJgjkin0izcE2ByQtbk1OrLEJ.1</a><br>
<br>
View meeting insights with Zoom AI Companion<br>
<a href="https://nam12.safelinks.protection.outlook.com/?url=https%3A%2F%2Ftamucc.zoom.us%2Flaunch%2Fedl%3Fmuid%3D7fc8dba1-82bc-433d-8739-8f383e7318a3&data=05%7C02%7Ccosc-grad-students-list%40listserv.tamucc.edu%7C49e624af4bca45f67b1f08de68f4da4e%7C34cbfaf167a64781a9ca514eb2550b66%7C0%7C0%7C639063598283628853%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=%2FCG7cPHGyPQEcnWzyxxe2wu9CrVZfeb9dqQXq9AmiGk%3D&reserved=0" originalsrc="https://tamucc.zoom.us/launch/edl?muid=7fc8dba1-82bc-433d-8739-8f383e7318a3">https://tamucc.zoom.us/launch/edl?muid=7fc8dba1-82bc-433d-8739-8f383e7318a3</a><br>
<br>
Meeting ID: 992 4689 2329<br>
Passcode: 098881<br>
<br>
---<br>
<br>
One tap mobile<br>
+13462487799,,99246892329#,,,,*098881# US (Houston)<br>
+12532158782,,99246892329#,,,,*098881# US (Tacoma)<br>
<br>
---<br>
<br>
Join by SIP<br>
• <a href="mailto:99246892329@zoomcrc.com">99246892329@zoomcrc.com</a><br>
Passcode: 098881<br>
<br>
Join instructions<br>
<a href="https://nam12.safelinks.protection.outlook.com/?url=https%3A%2F%2Ftamucc.zoom.us%2Fmeetings%2F99246892329%2Finvitations%3Fsignature%3D4yOALibkmMwty2qa6tM-6ODD0Tm5drYmebOlf4cYHsw&data=05%7C02%7Ccosc-grad-students-list%40listserv.tamucc.edu%7C49e624af4bca45f67b1f08de68f4da4e%7C34cbfaf167a64781a9ca514eb2550b66%7C0%7C0%7C639063598283646543%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=oOopt8aEbZfeMQOm3ajKgv%2Fw%2FbPmG3gNuhzuBjhmJNY%3D&reserved=0" originalsrc="https://tamucc.zoom.us/meetings/99246892329/invitations?signature=4yOALibkmMwty2qa6tM-6ODD0Tm5drYmebOlf4cYHsw">https://tamucc.zoom.us/meetings/99246892329/invitations?signature=4yOALibkmMwty2qa6tM-6ODD0Tm5drYmebOlf4cYHsw</a><br>
<br>
<br>
€€€€€€€€€€<o:p></o:p></p>
</div>
</body>
</html>