<div dir="ltr"><div dir="ltr"><div dir="ltr"><div><div class="gmail_default" style="font-size:small"><font style="font-family:arial,sans-serif;color:rgb(0,0,0);vertical-align:inherit"><font style="vertical-align:inherit"><b>When:</b> </font></font><font style="vertical-align:inherit"><font style="vertical-align:inherit"><font style="font-family:arial,sans-serif;color:rgb(0,0,0)"> Mon</font><span class="gmail_default" style="font-family:arial,sans-serif;color:rgb(0,0,0)">day, January 27,<span class="gmail_default"> </span>2025</span><font style="font-family:arial,sans-serif;color:rgb(0,0,0)"> at</font><b><font color="#000000" style="font-family:arial,sans-serif"> </font><u><font face="arial, sans-serif" color="#000000" style="background-color:rgb(255,255,0)">11:30</font></u></b><span style="background-color:rgb(255,255,0)"><font color="#000000"><b><u><font face="arial, sans-serif"> am</font></u></b><b><font face="arial, sans-serif"><u> CT</u> </font><font style="font-family:verdana,sans-serif"> </font><font style="font-family:verdana,sans-serif"> </font></b></font></span></font></font></div><div><div class="gmail_default"><div class="gmail_default"><div class="gmail_default"><p style="color:rgb(80,0,80);font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;line-height:normal;margin:0px"><b><font color="#500050" face="arial, sans-serif"><br></font></b></p><p style="color:rgb(80,0,80);font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;line-height:normal;margin:0px"><font face="arial, sans-serif"><b><font color="#500050">Where: </font></b><font color="#000000">Talk will be given </font><font color="#000000" style="font-weight:bold"><u>live, in-person</u></font><font style="font-weight:bold"> </font>at<br></font></p><p class="MsoNormal" style="margin:0in;color:rgb(80,0,80);line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="arial, sans-serif"><font color="#500050"> </font><font color="#000000"> TTIC, 6045 S. Kenwood Avenue</font></font></p><p class="MsoNormal" style="margin:0in;color:rgb(80,0,80);line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="arial, sans-serif" color="#000000"> 5th Floor, Room 530<b> </b></font></p><p class="MsoNormal" style="margin:0in;color:rgb(80,0,80);line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="arial, sans-serif"><b><span style="color:black"><br></span></b></font></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;color:rgb(80,0,80);line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="arial, sans-serif"><b style="color:rgb(60,64,67);letter-spacing:0.2px">Virtually:</b><span style="color:rgb(60,64,67);letter-spacing:0.2px"> <i>via panopto: </i><a href="https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=9066f6c5-1339-49c3-804c-b26b01470647" target="_blank"><b>livestream</b></a> </span></font></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;color:rgb(80,0,80);line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><b style="color:rgb(34,34,34);font-family:georgia,serif;letter-spacing:0.2px"><font size="1"> </font><font size="1" style="background-color:rgb(255,242,204)">Note: This has been restricted to TTIC/UChicago Only</font></b></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;color:rgb(80,0,80);line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><b style="color:rgb(60,64,67);letter-spacing:0.2px"><font size="1"><font face="georgia, serif"> </font></font></b><font face="arial, sans-serif"><br></font></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;color:rgb(80,0,80);line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><span style="color:rgb(60,64,67);letter-spacing:0.2px"><b><font face="arial, sans-serif"> </font></b></span></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="arial, sans-serif"><font style="color:rgb(80,0,80);vertical-align:inherit"><font style="vertical-align:inherit"><b>Who: </b> <font color="#500050"> </font><font color="#000000"><font color="#500050"> </font></font></font></font></font>Ruiqi Zhong, UC Berkeley</p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><br></p><div style="border-top:none;border-right:none;border-left:none;border-bottom:2.25pt solid rgb(11,118,159);padding:0in 0in 1pt"></div><div><br></div></div></div><div class="gmail_default"><div dir="ltr"><b>Title:</b> Building Strong Language Models from Weak Validators<br><br><b>Abstract: </b>Language models (LMs) can process large volumes of information and perform complex reasoning. They hold the promise of doing what experts struggle at, such as accelerating science or developing complex software. However, building these LMs requires humans to validate their outputs, which is challenging; e.g., developers cannot easily validate whether complex software is bug-free. If LMs optimize against weak human validations --- "appearing correct to humans" rather than being actually correct --- LMs will create a false impression that they can solve complex tasks, instead of actually solving them.<br><br>I propose three general approaches to assist human validators: 1) validating implications (e.g., the result of executing a program), 2) validating decompositions (e.g., well-factored programs), and 3) validating weak points (e.g., corner cases). Given the increasing capabilities of AI systems, developing effective validation strategies is critical to deploy them safely and prevent silent failures.<br><br><b>Bio:</b> Ruiqi Zhong is a final-year Ph.D. student at UC Berkeley, co-advised by Jacob Steinhardt and Dan Klein. He was previously a part-time member of technical staff at Anthropic, where he worked on the automated red teaming team. His research is at the intersection of machine learning and NLP, and he develops language model systems to advance the frontier of human capabilities.</div><div dir="ltr"><br></div></div></div></div><div><div class="gmail_default"><b style="font-family:arial,sans-serif">Host: </b><a href="mailto:klivescu@ttic.edu" style="font-family:arial,sans-serif" target="_blank"><b>Karen Livescu</b></a></div></div><br><br clear="all"></div><div><br></div><div><div dir="ltr" class="gmail_signature"><div dir="ltr"><div><span style="font-family:arial,helvetica,sans-serif;font-size:x-small">Mary C. Marre</span><br></div><div><div><font face="arial, helvetica, sans-serif" size="1">Faculty Administrative Support</font></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6" size="1"><b>Toyota Technological Institute</b></font></i></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6" size="1">6045 S. Kenwood Avenue, Rm 517</font></i></div><div><font size="1"><i><font face="arial, helvetica, sans-serif" color="#3d85c6">Chicago, IL 60637</font></i><br></font></div><div><font size="1"><i><font face="arial, helvetica, sans-serif" color="#3d85c6">773-834-1757</font></i></font></div><div><b><i><a href="mailto:mmarre@ttic.edu" target="_blank"><font face="arial, helvetica, sans-serif" size="1">mmarre@ttic.edu</font></a></i></b></div></div></div></div></div><br></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Mon, Jan 20, 2025 at 2:31 PM Mary Marre <<a href="mailto:mmarre@ttic.edu" target="_blank">mmarre@ttic.edu</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div><div style="font-size:small"><font style="font-family:arial,sans-serif;color:rgb(0,0,0);vertical-align:inherit"><font style="vertical-align:inherit"><b>When:</b> </font></font><font style="vertical-align:inherit"><font style="vertical-align:inherit"><font style="font-family:arial,sans-serif;color:rgb(0,0,0)"> Mon</font><span class="gmail_default" style="font-family:arial,sans-serif;color:rgb(0,0,0)">day, January 27,<span class="gmail_default"> </span>2025</span><font style="font-family:arial,sans-serif;color:rgb(0,0,0)"> at</font><b><font color="#000000" style="font-family:arial,sans-serif"> </font><u><font face="arial, sans-serif" color="#000000" style="background-color:rgb(255,255,0)">11:30</font></u></b><span style="background-color:rgb(255,255,0)"><font color="#000000"><b><u><font face="arial, sans-serif"> am</font></u></b><b><font face="arial, sans-serif"><u> CT</u> </font><font style="font-family:verdana,sans-serif"> </font><font style="font-family:verdana,sans-serif"> </font></b></font></span></font></font></div><div><div><div><div><p style="color:rgb(80,0,80);font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;line-height:normal;margin:0px"><b><font color="#500050" face="arial, sans-serif"><br></font></b></p><p style="color:rgb(80,0,80);font-variant-numeric:normal;font-variant-east-asian:normal;font-stretch:normal;line-height:normal;margin:0px"><font face="arial, sans-serif"><b><font color="#500050">Where: </font></b><font color="#000000">Talk will be given </font><font color="#000000" style="font-weight:bold"><u>live, in-person</u></font><font style="font-weight:bold"> </font>at<br></font></p><p class="MsoNormal" style="margin:0in;color:rgb(80,0,80);line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="arial, sans-serif"><font color="#500050"> </font><font color="#000000"> TTIC, 6045 S. Kenwood Avenue</font></font></p><p class="MsoNormal" style="margin:0in;color:rgb(80,0,80);line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="arial, sans-serif" color="#000000"> 5th Floor, Room 530<b> </b></font></p><p class="MsoNormal" style="margin:0in;color:rgb(80,0,80);line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="arial, sans-serif"><b><span style="color:black"><br></span></b></font></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;color:rgb(80,0,80);line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="arial, sans-serif"><b style="color:rgb(60,64,67);letter-spacing:0.2px">Virtually:</b><span style="color:rgb(60,64,67);letter-spacing:0.2px"> <i>via panopto: </i><a href="https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=9066f6c5-1339-49c3-804c-b26b01470647" target="_blank"><b>livestream</b></a> </span></font></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;color:rgb(80,0,80);line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><b style="color:rgb(34,34,34);font-family:georgia,serif;letter-spacing:0.2px"><font size="1"> </font><font size="1" style="background-color:rgb(255,242,204)">Note: This has been restricted to TTIC/UChicago Only</font></b></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;color:rgb(80,0,80);line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><b style="color:rgb(60,64,67);letter-spacing:0.2px"><font size="1"><font face="georgia, serif"> </font></font></b><font face="arial, sans-serif"><br></font></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;color:rgb(80,0,80);line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><span style="color:rgb(60,64,67);letter-spacing:0.2px"><b><font face="arial, sans-serif"> </font></b></span></p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><font face="arial, sans-serif"><font style="color:rgb(80,0,80);vertical-align:inherit"><font style="vertical-align:inherit"><b>Who: </b> <font color="#500050"> </font><font color="#000000"><font color="#500050"> </font></font></font></font></font>Ruiqi Zhong, UC Berkeley</p><p class="MsoNormal" style="margin:0in 0in 0.0001pt;line-height:normal;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><br></p><div style="border-top:none;border-right:none;border-left:none;border-bottom:2.25pt solid rgb(11,118,159);padding:0in 0in 1pt"></div><div><br></div></div></div><div><div dir="ltr"><b>Title:</b> Building Strong Language Models from Weak Validators<br><br><b>Abstract: </b>Language models (LMs) can process large volumes of information and perform complex reasoning. They hold the promise of doing what experts struggle at, such as accelerating science or developing complex software. However, building these LMs requires humans to validate their outputs, which is challenging; e.g., developers cannot easily validate whether complex software is bug-free. If LMs optimize against weak human validations --- "appearing correct to humans" rather than being actually correct --- LMs will create a false impression that they can solve complex tasks, instead of actually solving them.<br><br>I propose three general approaches to assist human validators: 1) validating implications (e.g., the result of executing a program), 2) validating decompositions (e.g., well-factored programs), and 3) validating weak points (e.g., corner cases). Given the increasing capabilities of AI systems, developing effective validation strategies is critical to deploy them safely and prevent silent failures.<br><br><b>Bio:</b> <span>Ruiqi</span> <span>Zhong</span> is a final-year Ph.D. student at UC Berkeley, co-advised by Jacob Steinhardt and Dan Klein. He was previously a part-time member of technical staff at Anthropic, where he worked on the automated red teaming team. His research is at the intersection of machine learning and NLP, and he develops language model systems to advance the frontier of human capabilities.</div><div dir="ltr"><br></div></div></div></div><div><div><b style="font-family:arial,sans-serif">Host: </b><a href="mailto:klivescu@ttic.edu" style="font-family:arial,sans-serif" target="_blank"><b>Karen Livescu</b></a></div></div><br><br clear="all"></div><div><br></div><div><br></div><div><br></div><div><div dir="ltr" class="gmail_signature"><div dir="ltr"><div><span style="font-family:arial,helvetica,sans-serif;font-size:x-small">Mary C. Marre</span><br></div><div><div><font face="arial, helvetica, sans-serif" size="1">Faculty Administrative Support</font></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6" size="1"><b>Toyota Technological Institute</b></font></i></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6" size="1">6045 S. Kenwood Avenue, Rm 517</font></i></div><div><font size="1"><i><font face="arial, helvetica, sans-serif" color="#3d85c6">Chicago, IL 60637</font></i><br></font></div><div><font size="1"><i><font face="arial, helvetica, sans-serif" color="#3d85c6">773-834-1757</font></i></font></div><div><b><i><a href="mailto:mmarre@ttic.edu" target="_blank"><font face="arial, helvetica, sans-serif" size="1">mmarre@ttic.edu</font></a></i></b></div></div></div></div></div></div>
</blockquote></div></div>
</div>