BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//hacksw/handcal//NONSGML v1.0//EN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20260411T025351Z
DESCRIPTION:Click for Latest Location Information: http://dgiq-edw2026.data
 versity.net/sessionPop.cfm?confid=165&proposalid=16551\nData quality automa
 tion is experiencing a fundamental shift. While rule-based systems operate 
 according to logics determined by human experts, data-driven approaches usi
 ng machine learning learn from observations and training data to identify p
 atterns associated with normal or fault conditions. Now, large language mod
 els like GPT, LLaMA, and Claude have exhibited considerable potential in da
 ta wrangling tasks, with even smaller fine-tuned 7B and 13B models showing 
 comparable capabilities in several data cleaning tasks.\n\nThis session exp
 lores both traditional machine learning and emerging LLM approaches to data
  quality. Recent research investigates whether LLMs can effectively preproc
 ess noisy textual data, with experimental results showing improvements when
  using LLM-cleaned captions, though statistical tests reveal most improveme
 nts are not yet significant. Attendees will learn evidence-based frameworks
  for when to use statistical ML versus LLM-based approaches, understand the
 ir complementary strengths, and gain practical decision criteria for implem
 entation.
DTSTART:20260506T093000
SUMMARY:The Evolution of AI-Driven Data Quality: From Traditional ML to Lar
 ge Language Models
DTEND:20260506T101459
LOCATION: See Description
END:VEVENT
END:VCALENDAR