BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T143005Z
LOCATION:B302-B305
DTSTART;TZID=America/New_York:20241119T120000
DTEND;TZID=America/New_York:20241119T170000
UID:submissions.supercomputing.org_SC24_sess487_post191@linklings.com
SUMMARY:Mind Your Manners: Detoxifying Language Models via Attention Head 
 Intervention
DESCRIPTION:Jordan Pettyjohn (Colorado School of Mines)\n\nTransformer-bas
 ed Large Language Models have advanced natural language processing with th
 eir ability to generate fluent text. However, these models exhibit and amp
 lify toxicity and bias learned from training data, posing new ethical chal
 lenges. We build upon the \attnlens{} framework to allow for scalable deco
 ding of attention mechanism information. We then use this decoded informat
 ion to implement a pipeline to generate and remove toxic memories from pre
 -trained language models in a way that is both human interpretable and eff
 ective while retaining model performance.\n\nRegistration Category: Tech P
 rogram Reg Pass, Exhibits Reg Pass\n\nSession Chairs: Ayesha Afzal (Friedr
 ich-Alexander-Universität Erlangen-Nürnberg, Erlangen National High Perfor
 mance Computing Center); Sally Ellingson (University of Kentucky); and Ala
 n Sussman (University of Maryland)\n\n
END:VEVENT
END:VCALENDAR