Skip to content

Commit

Permalink
Update index.html
Browse files Browse the repository at this point in the history
  • Loading branch information
@asuvarna31
asuvarna31 authored Dec 9, 2024
1 parent 7459912 commit 97f4d58
Showing 1 changed file with 56 additions and 36 deletions.
92 changes: 56 additions & 36 deletions index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -42,40 +42,6 @@ <h1>UCLA NLP Seminar Series</h1>
</div>
</nav>

<main>
<h2>Talk Schedule for Fall 2024</h2>
<table class="seminar-schedule">
<thead>
<tr>
<th>Date</th>
<th>Speaker</th>
<th>Title</th>
</tr>
</thead>
<tbody>
<tr>
<td>Oct 25</td>
<td><a href="https://www.coalas-lab.com/elisakreiss">Elisa Kreiss</a></td>
<td>Translating images into words: From truthful to useful</td>
</tr>
<tr>
<td>Nov 1</td>
<td><a href="https://jyzhao.net/">Jieyu Zhao</a></td>
<td>Building Accountable NLP Models for Social Good</td>
</tr>
<tr>
<td>Nov 5</td>
<td><a href="https://robinjia.github.io/">Robin Jia</a></td>
<td>Auditing, Understanding, and Leveraging Large Language Models</td>
</tr>
<!-- <tr>
<td>Oct 24</td>
<td>Jieyu Zhao</td>
<td>Building Accountable NLP Models for Social Good <a href="#" class="details-link">(details)</a></td>
</tr> -->
</tbody>
</table>

<h2>Talk Schedule for Winter 2025</h2>
<table class="seminar-schedule">
<thead>
Expand All @@ -89,7 +55,7 @@ <h2>Talk Schedule for Winter 2025</h2>
<tr>
<td>Jan 10</td>
<td><a href="https://swabhs.com/">Swabha Swayamdipta</a></td>
<!-- <td>Translating images into words: From truthful to useful</td> -->
<td>Ensuring Safety and Accountability in LLMs, Pre- and Post Training</td>
</tr>
<tr>
<td>Jan 17</td>
Expand Down Expand Up @@ -122,9 +88,63 @@ <h2>Talk Schedule for Winter 2025</h2>
<!-- <h2>&#128680; Happening Today </h2> -->


<!-- <h2>&#128640; Upcoming Talks </h2> -->
<h2>&#128640; Upcoming Talks </h2>
<div class="talk" onclick="toggleDetails(this)">
<div class="talk-summary">
<div class="date">
<div class="month">JAN</div>
<div class="day">10</div>
</div>
<div class="speaker-image">
<a href="https://swabhs.com/" target="_block">
<img src="https://drive.google.com/file/d/1Et4TTmUIsKFeVGwJM8415DcuSYGzgPtu/view?usp=sharing" alt="Prof. Swabha Swayamdipta" style="max-height: 300px;"/>
</a>
</div>
<div class="speaker-text">
<h3>Auditing, Understanding, and Leveraging Large Language Models</h3>
<p><img src="icons/person.png" alt="Person Icon" class="icon"><a href="https://swabhs.com/">Swabha Swayamdipta</a></p>
<p><img src="icons/clock.png" alt="Clock Icon" class="icon">Jan 10, 2024, 2:00 PM</p>
<p><img src="icons/location.png" alt="Location Icon" class="icon">289, Engineering VI</p>
<!-- <p><img src="icons/zoom.png" alt="Zoom Icon" class="icon">To Be Announced</p> -->
</div>
<div class="footer">
<button class="more-details">More Details</button>
</div>
</div>
<div class="talk-details">
<p><strong>Speaker Bio:</strong> Swabha Swayamdipta is an Assistant Professor of Computer Science and a Gabilan Assistant Professor at the University of Southern California. Her research interests lie in natural language processing and machine learning, with a primary focus on the evaluation of generative models of language, understanding the behavior of language models, and designing language technologies for societal good. At USC, Swabha leads the Data, Interpretability, Language, and Learning (DILL) Lab. She received her PhD from Carnegie Mellon University, followed by a postdoctoral position at the Allen Institute for AI. Her work has received awards at EMNLP, ICML, NeurIPS, and ACL. Her research is supported by awards from the National Science Foundation, the Allen Institute for AI, and a Rising Star Award from Intel Labs.</p>
<p><strong>Abstract:</strong> As large language models have become ubiquitous, it has proven increasingly challenging to enforce their accountability and safe deployment. In this talk, I will discuss the importance of ensuring the safety, responsibility, and accountability of Large Language Models (LLMs) throughout all stages of their development: pre-training, post-training evaluation, and deployment. First, I will present the idea of a unique LLM signature that can identify the model to ensure accountability. Next, I will present our recent work on reliably evaluating LLMs through our novel formulation of generation separability, and how this could lead to more reliable generation. Finally, I will present some ongoing work that demonstrates LLMs' ability to understand but not generate unsafe or untrustworthy content. </p>
</div>
</div>


<!-- <div class="talk" onclick="toggleDetails(this)">
<div class="talk-summary">
<div class="date">
<div class="month">JAN</div>
<div class="day">10</div>
</div>
<div class="speaker-image">
<a href="https://swabhs.com/" target="_block">
<img src="Image Link" alt="Speaker Name" style="max-height: 300px;"/>
</a>
</div>
<div class="speaker-text">
<h3>Talk Title</h3>
<p><img src="icons/person.png" alt="Person Icon" class="icon"><a href="Speaker Website">Speaker Name</a></p>
<p><img src="icons/clock.png" alt="Clock Icon" class="icon">Jan 10, 2024, 2:00 PM</p>
<p><img src="icons/location.png" alt="Location Icon" class="icon">289, Engineering VI</p>
<p><img src="icons/zoom.png" alt="Zoom Icon" class="icon">To Be Announced</p>
</div>
<div class="footer">
<button class="more-details">More Details</button>
</div>
</div>
<div class="talk-details">
<p><strong>Speaker Bio:</strong> INSERT BIO </p>
<p><strong>Abstract:</strong> INSERT TALK ABSTRACT HERE </p>
</div>
</div> -->


<h2>Organizing Committee</h2>
Expand Down

0 comments on commit 97f4d58

Please sign in to comment.