Skip to content

Commit ffafb71

Browse files
authored
Add presentation details for Marwa Abdulhai
Added details for a presentation by Marwa Abdulhai, including the paper title, presenter information, and abstract.
1 parent d0e011d commit ffafb71

1 file changed

Lines changed: 28 additions & 0 deletions

File tree

stamina/index.html

Lines changed: 28 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -190,6 +190,34 @@ <h4>[DATE Y/M/D]</h4>
190190

191191
<br>
192192

193+
<h4>2026/05/05</h4>
194+
<li>
195+
<b><a href="[PAPER LINK]">Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning</a></b>
196+
<br>
197+
Presenter: <u><a href="[PRESENTER URL]" target="_blank" rel="noopener noreferrer">[PRESENTER NAME]</a></u>, [PRESENTER AFFILIATION]
198+
<a class="btn btn-info btn-xs" data-toggle="collapse" href="#20260505-bio" role="button" aria-expanded="false">
199+
Speaker Bio
200+
</a>
201+
<div class="collapse" id="20260505-bio">
202+
<div class="card card-body">
203+
Marwa Abdulhai is a PhD candidate at UC Berkeley advised by Sergey Levine. Her research focuses on enabling AI agents to better understand people and their interactions to build both safe and more AI capable systems. This includes improving the performance of existing large language models (LLMs) for multi-turn dialogue interactions, understanding how to protect against deception in AI systems, and exploring how AI can serve as a useful tool for social science research. Her research has been supported by the Quad Fellowship, AI Policy Hub, Open AI Research, and Cooperative AI PhD Fellowship.
204+
</div>
205+
</div>
206+
<br>
207+
<!-- <a href="[RECORDING LINK - ADD AFTER TALK]"><img src="https://img.shields.io/badge/Youtube-Recording-orange"></a> -->
208+
<!-- <a href="[PAPER LINK]"><img src="https://img.shields.io/badge/Paper-link-important"></a> -->
209+
<a href="https://abdulhaim.github.io/"><img src="https://img.shields.io/badge/Github-link-lightgrey"></a>
210+
<!-- <a href="[SLIDES_LINK]"><img src="https://img.shields.io/badge/Talk-Slides-blue"></a> -->
211+
<a class="btn btn-primary btn-xs" data-toggle="collapse" href="#20260505-abstract" role="button" aria-expanded="false">
212+
Abstract
213+
</a>
214+
<div class="collapse" id="20260505-abstract">
215+
<div class="card card-body">
216+
Large Language Models (LLMs) are increasingly used to simulate human users in interactive settings such as therapy, education, and social role-play. While these simulations enable scalable training and evaluation of AI agents, off-the-shelf LLMs often drift from their assigned personas, contradict earlier statements, or abandon role-appropriate behavior. We introduce a unified framework for evaluating and improving consistency in LLM-generated dialogue with multi-turn RL, reducing inconsistency by over 55%, resulting in more coherent and trustworthy simulated users.
217+
</div>
218+
</div>
219+
</li>
220+
193221
<h4>2026/04/28</h4>
194222
<li>
195223
<b><a href="[PAPER LINK]">From Social Networks to Sensemaking Networks</a></b>

0 commit comments

Comments
 (0)