BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260616T150257Z
UID:b8a72a80-f58b-4b39-92c8-43c33d33ded0
DTSTART:20250402T090000Z
DTEND:20250402T170000Z
DESCRIPTION:This webinar will explore how Large Language Models (LLMs) can 
 streamline the extraction of critical information from scientific texts\, 
 focusing on patient-derived cancer models (PDCMs). PDCMs are vital tools f
 or cancer research and preclinical studies\, with a growing body of litera
 ture in this field. However\, manually extracting and curating information
  from scientific texts is labor-intensive and prone to delays. In this ses
 sion\, we will introduce two innovative approaches: direct prompting and s
 oft prompting. Direct prompting uses manually created instructions to extr
 act PDCM-related entities\, while soft prompting leverages machine learnin
 g to train continuous vector prompts. We will discuss our comparative eval
 uation using state-of-the-art proprietary and open-source LLMs\, demonstra
 ting how tailored prompt engineering can elevate the performance of smalle
 r\, open models to match proprietary counterparts. This session will highl
 ight the potential of LLMs to enhance domain-specific knowledge extraction
  and accelerate research workflows.
LOCATION:\, 
SUMMARY:Domain-specific knowledge extraction from scientific texts using LL
 Ms
URL;VALUE=URI:https://www.ebi.ac.uk/training/events/domain-specific-knowled
 ge-extraction-scientific-texts-using-llms
END:VEVENT
END:VCALENDAR