BEGIN:VCALENDAR
METHOD:PUBLISH
PRODID:Microsoft Exchange Server 2010
VERSION:2.0
BEGIN:VTIMEZONE
TZID:tzone://Microsoft/Utc
BEGIN:STANDARD
DTSTART:16010101T000000
TZOFFSETFROM:+0000
TZOFFSETTO:+0000
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:16010101T000000
TZOFFSETFROM:+0000
TZOFFSETTO:+0000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
ORGANIZER;CN="Giampouras, Paris":mailto:Paris.Giampouras@warwick.ac.uk
DESCRIPTION:Speaker: Ilija Bogunovic\nDate: 2024-10-22\nAbstract\Aligning large language models (LLMs) with human values, ethical principles, and user intentions is critical to building AI systems like ChatGPT that drive transformative, human-centric progress. It is also a key step toward ensuring the sustainable and safe development of artificial general intelligence (AGI) that genuinely benefits humanity. Reinforcement learning from human feedback (RLHF) has become the leading method for fine-tuning LLMs, optimizing their responses by using human preferences to guide their behavior. However, RLHF faces pressing challenges—namely, inefficient data use and an overly simplified approach to the complex, pluralistic nature of human societies. RLHF-tuned models frequently exhibit bias, favoring majority perspectives while overlooking minority voices, highlighting the need for principled algorithms that address these shortcomings. In this talk, we present innovative, efficient, and pluralistic alignment algorithms that outperform standard RLHF methods. Our approach tackles data acquisition inefficiencies, improves bias resilience, and aligns LLMs with a wider range of human perspectives. By integrating RLHF with sequential decision-making frameworks, we significantly boost data efficiency and develop algorithms capable of navigating the complexities of aligning LLMs with diverse societal values. We showcase our algorithms' effectiveness in fine-tuning popular LLM models.\n\n
UID:040000008200E00074C5B7101A82E008000000001DE3EE31A094DA01000000000000000
01000000070FE3FC3C2CFBC4B9BC78D79F05EDB89
SUMMARY:Foundations of AI Seminars - Ilija Bogunovic 
DTSTART:20241022T140000Z
DTEND:20241022T150000Z
CLASS:PUBLIC
PRIORITY:5
DTSTAMP:20241022T103151Z
TRANSP:OPAQUE
STATUS:CONFIRMED
LOCATION:CS1.04
X-MICROSOFT-CDO-BUSYSTATUS:BUSY
X-MICROSOFT-CDO-INTENDEDSTATUS:BUSY
X-MICROSOFT-CDO-ALLDAYEVENT:FALSE
X-MICROSOFT-CDO-IMPORTANCE:1
X-MICROSOFT-CDO-INSTTYPE:0
X-MICROSOFT-ONLINEMEETINGEXTERNALLINK:
X-MICROSOFT-ONLINEMEETINGCONFLINK:
X-MICROSOFT-DONOTFORWARDMEETING:FALSE
X-MICROSOFT-DISALLOW-COUNTER:FALSE
X-MICROSOFT-LOCATIONDISPLAYNAME:CS1.04
BEGIN:VALARM
DESCRIPTION:REMINDER
TRIGGER;RELATED=START:-PT14M
ACTION:DISPLAY
END:VALARM
END:VEVENT