<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">
<style type="text/css" style="display:none;"> P {margin-top:0;margin-bottom:0;} </style>
</head>
<body dir="ltr">
<div class="elementToProof" style="direction: ltr; text-align: left; text-indent: 0px; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt; padding: 0pt 0pt 10pt; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; color: rgb(0, 0, 0);">
<span style="font-size: 14pt; font-weight: 700;">Call for Papers for the L2M2 workshop</span><span style="font-size: 14pt;"><br>
</span><span style="font-size: 12pt;">Large language models (LLMs) are known to memorize their training data. In recent years, this phenomenon has inspired multiple distinct research directions. Some researchers currently focus on analyzing and understanding
LLM memorization, attempting to localize memorized knowledge within a model or understand which examples are most likely to be memorized. Other researchers aim to edit or remove information that an LLM has memorized. Still, others study the downstream implications
of LLM memorization, including legal concerns associated with memorizing copyrighted articles, privacy risks associated with LLMs leaking private information, and concerns that LLMs cheat on benchmarks by memorizing test data.</span></div>
<div style="direction: ltr; text-align: left; text-indent: 0px; line-height: 1.38; margin-top: 0pt; margin-bottom: 10pt; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt;">
<span style="color: rgb(0, 0, 0);">The </span><span style="color: rgb(204, 0, 0);"><u><a href="https://sites.google.com/view/memorization-workshop/home" target="_blank" id="OWAb755bf20-7c9c-2cc7-0ed3-6674c4ed1391" class="OWAAutoLink" data-saferedirecturl="https://www.google.com/url?q=https://sites.google.com/view/memorization-workshop/home&source=gmail&ust=1738142915328000&usg=AOvVaw3rZfOTtm3mzskSOUmojLrh" style="color: rgb(204, 0, 0);">First
Workshop on Large Language Model Memorization (L2M2),</a></u></span><span style="color: rgb(0, 0, 0);"> co-located with
</span><span style="color: rgb(204, 0, 0);"><u><a href="https://2025.aclweb.org/" target="_blank" id="OWAdd90ab55-18dd-81d4-e6ac-0e2a6633569f" class="OWAAutoLink" data-saferedirecturl="https://www.google.com/url?q=https://2025.aclweb.org/&source=gmail&ust=1738142915328000&usg=AOvVaw2sfVBQ90872aSKcssLqJbb" style="color: rgb(204, 0, 0);">ACL
2025</a></u></span><span style="color: rgb(0, 0, 0);"> in Vienna, seeks to provide a central venue for researchers studying LLM memorization from these different angles. We invite paper submissions on all topics related to LLM memorization, including but not
limited to:</span></div>
<ul style="text-align: left; margin-top: 0px; margin-bottom: 0px;">
<li style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); direction: ltr; white-space: pre-wrap; margin-left: 15px; list-style-type: disc;">
<div style="direction: ltr; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;">
Behavioral analyses that seek to understand what training data is memorized by models.</div>
</li><li style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); direction: ltr; white-space: pre-wrap; margin-left: 15px; list-style-type: disc;">
<div style="direction: ltr; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;">
Methods for measuring the extent to which models memorize training data.</div>
</li><li style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); direction: ltr; white-space: pre-wrap; margin-left: 15px; list-style-type: disc;">
<div style="direction: ltr; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;">
Interpretability work analyzing how models memorize training data.</div>
</li><li style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); direction: ltr; white-space: pre-wrap; margin-left: 15px; list-style-type: disc;">
<div style="direction: ltr; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;">
The relationship between training data memorization and membership inference.</div>
</li><li style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); direction: ltr; white-space: pre-wrap; margin-left: 15px; list-style-type: disc;">
<div style="direction: ltr; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;">
Analyses of how memorization of training data is related to generalization and model capabilities.</div>
</li><li style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); direction: ltr; white-space: pre-wrap; margin-left: 15px; list-style-type: disc;">
<div style="direction: ltr; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;">
Methods or benchmarks for preventing models from outputting memorized data, such as machine unlearning, model editing, or output filtering techniques.</div>
</li><li style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); direction: ltr; white-space: pre-wrap; margin-left: 15px; list-style-type: disc;">
<div style="direction: ltr; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;">
Model editing techniques for modifying knowledge that models have memorized.</div>
</li><li style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); direction: ltr; white-space: pre-wrap; margin-left: 15px; list-style-type: disc;">
<div style="direction: ltr; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;">
Legal implications and risks of LLM memorization.</div>
</li><li style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); direction: ltr; white-space: pre-wrap; margin-left: 15px; list-style-type: disc;">
<div style="direction: ltr; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;">
Privacy and security risks of LLM memorization.</div>
</li><li style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); direction: ltr; white-space: pre-wrap; margin-left: 15px; list-style-type: disc;">
<div style="direction: ltr; line-height: 1.38; margin-top: 0pt; margin-bottom: 8pt;">
Implications of memorization for benchmarking, such as data contamination concerns.</div>
</li></ul>
<div style="direction: ltr; text-align: left; text-indent: 0px; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt; padding: 0pt 0pt 10pt; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Any models that process or generate text are in scope for this workshop, including text-only language models, vision language models, machine translation models, etc. Memorization in the context of L2M2 could refer to verbatim memorization of training data,
approximate memorization of copyrighted content, memorization of factual knowledge, memorization of correct answers to questions, or other definitions.</div>
<div class="elementToProof" style="direction: ltr; text-align: left; text-indent: 0px; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt; padding: 0pt 0pt 10pt; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt;">
<span style="color: rgb(0, 0, 0);">If you have any questions about whether your paper is suitable for our workshop, feel free to contact us at</span><span style="color: rgb(200, 38, 19);">
<u><a href="mailto:l2m2-workshop@googlegroups.com" target="_blank" id="OWAf75187f2-38ce-8833-23cb-c3aefa2b84a5" class="OWAAutoLink" style="color: rgb(200, 38, 19);">l2m2-workshop@googlegroups.com</a></u></span><span style="color: rgb(0, 0, 0);"><wbr style="color: rgb(0, 0, 0);">.</span></div>
<div style="direction: ltr; text-align: left; text-indent: 0px; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt; padding: 0pt 0pt 10pt; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt;">
<span style="color: rgb(0, 0, 0); font-weight: 700;">Submission Guidelines</span><span style="color: rgb(0, 0, 0);"><br>
We seek submissions of at least 4 and at most 8 pages, not including references. All submissions will be reviewed in a single track, regardless of length. Please format your papers using
</span><span style="color: rgb(204, 0, 0);"><u><a href="https://www.overleaf.com/latex/templates/association-for-computational-linguistics-acl-conference/jvxskxpnznfj" target="_blank" id="OWA3b515e5a-f95d-4ac0-25c9-ebce4ffa6f15" class="OWAAutoLink" data-saferedirecturl="https://www.google.com/url?q=https://www.overleaf.com/latex/templates/association-for-computational-linguistics-acl-conference/jvxskxpnznfj&source=gmail&ust=1738142915328000&usg=AOvVaw3mJft-sDCjfpH4WReXa4YL" style="color: rgb(204, 0, 0);">the
standard ACL format</a></u></span><span style="color: rgb(0, 0, 0);">. We will accept direct submissions via
</span><span style="color: rgb(204, 0, 0);"><u><a href="https://openreview.net/group?id=aclweb.org/ACL/2025/Workshop/L2M2#tab-recent-activity" target="_blank" id="OWA2e46d7c5-df5e-d268-3051-57c45e09a3f0" class="OWAAutoLink" data-saferedirecturl="https://www.google.com/url?q=https://openreview.net/group?id%3Daclweb.org/ACL/2025/Workshop/L2M2%23tab-recent-activity&source=gmail&ust=1738142915328000&usg=AOvVaw1iPcFc4M1bkn3KG5iXHWF7" style="color: rgb(204, 0, 0);">OpenReview</a></u></span><span style="color: rgb(0, 0, 0);">,
as well as submissions made through ACL Rolling Review.</span></div>
<div style="direction: ltr; text-align: left; text-indent: 0px; line-height: 1.38; margin-top: 0pt; margin-bottom: 10pt; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
We accept two types of submissions:</div>
<ol start="1" style="text-align: left; margin-top: 0px; margin-bottom: 0px;">
<li style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); direction: ltr; white-space: pre-wrap; margin-left: 15px; list-style-type: decimal;">
<div style="direction: ltr; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;">
<i>Archival</i>: Original work that will be included in the workshop proceedings. Submissions must be anonymized and will go through a double-blind review process.</div>
</li><li style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); direction: ltr; white-space: pre-wrap; margin-left: 15px; list-style-type: decimal;">
<div style="direction: ltr; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;">
<i>Non-archival</i>: Such submissions will not be included in the proceedings. The workshop will accept two categories of non-archival work:</div>
</li><ul style="margin-top: 0px; margin-bottom: 0px;">
<li style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); direction: ltr; white-space: pre-wrap; margin-left: 15px; list-style-type: circle;">
<div style="direction: ltr; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;">
Work published elsewhere: The authors should indicate the original venue, and will be accepted if the organizers think the work will benefit from exposure to the audience of this workshop. Submissions do not need to be anonymized.</div>
</li><li style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); direction: ltr; white-space: pre-wrap; margin-left: 15px; list-style-type: circle;">
<div style="direction: ltr; line-height: 1.38; margin-top: 0pt; margin-bottom: 8pt;">
Work-in-progress: These may report on work in progress that have not yet been published at a different venue. The acceptance will be based on a double-blind review and thus submissions of this type need to be anonymized.</div>
</li></ul>
</ol>
<div style="direction: ltr; text-align: left; text-indent: 0px; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt; padding: 0pt 0pt 10pt; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<span style="font-weight: 700;">Dual submissions</span><br>
We allow submissions that are also under review in other venues, but please note that many conferences do not allow it, so make sure that you do not violate their policy as well.</div>
<div style="direction: ltr; text-align: left; text-indent: 0px; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt; padding: 0pt 0pt 10pt; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<span style="font-weight: 700;">Anonymity period</span><br>
We do not have an anonymity deadline. Preprints are allowed, both before the submission deadline as well as after.</div>
<div style="direction: ltr; text-align: left; text-indent: 0px; line-height: 1.38; margin-top: 0pt; margin-bottom: 10pt; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<span style="font-weight: 700;">Important Dates</span></div>
<ul style="text-align: left; margin-top: 0px; margin-bottom: 0px;">
<li style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); direction: ltr; white-space: pre-wrap; margin-left: 15px; list-style-type: disc;">
<div style="direction: ltr; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;">
Latest submission date for ARR submissions: February 15, 2025</div>
</li><li style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); direction: ltr; white-space: pre-wrap; margin-left: 15px; list-style-type: disc;">
<div style="direction: ltr; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;">
Direct submission deadline: March 25, 2025</div>
</li><li style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); direction: ltr; white-space: pre-wrap; margin-left: 15px; list-style-type: disc;">
<div style="direction: ltr; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;">
Pre-reviewed (ARR) commitment deadline: April 17, 2025</div>
</li><li style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); direction: ltr; white-space: pre-wrap; margin-left: 15px; list-style-type: disc;">
<div style="direction: ltr; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;">
Notification of acceptance: April 27, 2025</div>
</li><li style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); direction: ltr; white-space: pre-wrap; margin-left: 15px; list-style-type: disc;">
<div style="direction: ltr; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;">
Camera-ready paper deadline: May 16, 2025</div>
</li><li style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); direction: ltr; white-space: pre-wrap; margin-left: 15px; list-style-type: disc;">
<div style="direction: ltr; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;">
Proceedings due (hard deadline): June 30, 2025</div>
</li><li style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); direction: ltr; white-space: pre-wrap; margin-left: 15px; list-style-type: disc;">
<div style="direction: ltr; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;">
Pre-recorded video due (hard deadline): July 7, 2025</div>
</li><li style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); direction: ltr; white-space: pre-wrap; margin-left: 15px; list-style-type: disc;">
<div style="direction: ltr; line-height: 1.38; margin-top: 0pt; margin-bottom: 8pt;">
Workshop dates: July 31st - August 1st 2025</div>
</li></ul>
<div class="elementToProof" style="direction: ltr; text-align: left; text-indent: 0px; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt; padding: 0pt 0pt 10pt; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Note: all deadlines are 11:59PM UTC-12:00.</div>
<div class="elementToProof" style="direction: ltr; text-align: left; text-indent: 0px; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<i>The organizers:</i></div>
<div style="direction: ltr; text-align: left; text-indent: 0px; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Robin Jia</div>
<div style="direction: ltr; text-align: left; text-indent: 0px; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Eric Wallace</div>
<div class="elementToProof" style="direction: ltr; text-align: left; text-indent: 0px; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Yangsibo Huang</div>
<div style="direction: ltr; text-align: left; text-indent: 0px; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Tiago Pimentel</div>
<div style="direction: ltr; text-align: left; text-indent: 0px; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Pratyush Maini</div>
<div class="elementToProof" style="direction: ltr; text-align: left; text-indent: 0px; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Verna Dankers</div>
<div style="direction: ltr; text-align: left; text-indent: 0px; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Johnny Wei</div>
<div style="direction: ltr; text-align: left; text-indent: 0px; line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt; font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Pietro Lesci</div>
<div class="elementToProof" style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. Is e buidheann carthannais a th’ ann an Oilthigh Dhùn Èideann, clàraichte an Alba, àireamh clàraidh SC005336.
</body>
</html>