BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.4.0.1//EN
TZID:Asia/Kolkata
X-WR-TIMEZONE:Asia/Kolkata
BEGIN:VEVENT
UID:220@cds.iisc.ac.in
DTSTART;TZID=Asia/Kolkata:20260901T100000
DTEND;TZID=Asia/Kolkata:20260901T110000
DTSTAMP:20260813T165311Z
URL:https://cds.iisc.ac.in/events/seminar-cds-102-september-01st-1000-from
 -papers-to-insights-with-llms-and-knowledge-graphs/
SUMMARY:{Seminar} @ CDS: #102\, September 01st: 10:00: "From Papers to Insi
 ghts with LLMs and Knowledge Graphs."
DESCRIPTION:Department of Computational and Data Sciences\nDepartment Semin
 ar\n\n\n\nSpeaker : Prof. Michael Färber\, Professor (W3) at the AI Cente
 r ScaDS.AI and TU Dresden\, Germany\nTitle : From Papers to Insights with 
 LLMs and Knowledge Graphs\nDate &amp\; Time : September 01st\, 2026 (Tuesd
 ay)\, 10:00 AM\nVenue : # 102\, CDS Seminar Hall\n\n\n\nABSTRACT:\nScience
  is producing knowledge faster than any human can read. The key challenge 
 is therefore no longer access to papers\, but turning them into reliable\,
  verifiable insights. In this talk\, I explain how large language models a
 nd knowledge graphs can work together to extract claims and evidence from 
 the literature\, connect information at scale\, and generate answers that 
 remain traceable to sources. I also discuss "AI with a conscience" and pre
 sent practical methods for controlling model behavior through prompting an
 d constrained inference. In addition\, I outline mechanisms that flag unce
 rtainty and potentially harmful outputs and enable knowledge updates witho
 ut full retraining. The goal is to build AI systems that support scientist
 s while remaining transparent\, controllable\, and aligned with human valu
 es.\n\nBIOGRAPHY:\nProf. Dr.-Ing. Michael Färber (https://faerber-lab.git
 hub.io/) is a Full Professor (W3) at the AI Center ScaDS.AI and TU Dresden
 \, Germany\, where he leads the "Scalable Software Architectures for Data 
 Analytics" group. He previously served as Deputy Full Professor for Web Sc
 ience at the Karlsruhe Institute of Technology (KIT). His research focuses
  on large language models\, knowledge graphs\, and graph neural networks\,
  with an emphasis on trustworthy AI for science. He develops systems for l
 arge-scale analysis of scientific literature and evidence-grounded text ge
 neration with verifiable citations. He has published 130+ peer-reviewed pa
 pers at venues such as AAAI\, ACL\, EMNLP\, CIKM\, KDD\, NAACL\, and ICML.
 \n\nHost Faculty: Dr. Danish Pruthi\n\n\n\nALL ARE WELCOME
CATEGORIES:Events,Talks
END:VEVENT
BEGIN:VTIMEZONE
TZID:Asia/Kolkata
X-LIC-LOCATION:Asia/Kolkata
BEGIN:STANDARD
DTSTART:20250901T100000
TZOFFSETFROM:+0530
TZOFFSETTO:+0530
TZNAME:IST
END:STANDARD
END:VTIMEZONE
END:VCALENDAR