BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Eventi DIAG
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20241027T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RDATE:20251026T030000
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20250330T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.28700.field_data.0@oba.diag.uniroma1.it
DTSTAMP:20260410T144441Z
CREATED:20250328T090244Z
DESCRIPTION:Abstract:With the rise of pre-trained Large Language Models (LL
 Ms)\, there is now an effective solution to store and use information extr
 acted from massive corpora of documents. However\, for data-intensive task
 s over structured data\, relational DBs and SQL queries are at the core of
  countless applications. While these two technologies may appear distant\,
  in this talk we will see that they can interact effectively and with prom
 ising results. LLMs can help users express SQL queries (Semantic Parsing)\
 , but SQL queries can be used to evaluate LLMs (Benchmarking). Their combi
 nation can be further advanced\, with opportunities to query with a unifie
 d SQL interface both LLMs and DBs. We present recent results on these topi
 cs and then conclude with an overview of the research challenges in effect
 ively leveraging the combined power of SQL and LLMs.Bio:Paolo Papotti is a
 n Associate Professor at EURECOM (France) since 2017 and the holder of a C
 hair of Artificial Intelligence at the 3IA Institute since 2024. He got hi
 s PhD from Roma Tre University (Italy) in 2007 and had research positions 
 at the Qatar Computing Research Institute (Qatar) and Arizona State Univer
 sity (USA). His research is focused on data management and NLP. He has aut
 hored more than 170 publications and his work has been recognized with bes
 t paper awards (CIKM 2024\, ISWC 2024)\, two “Best of the Conference” cita
 tions (SIGMOD 2009\, VLDB 2016)\, three best demo awards (SIGMOD 2015\, DB
 A 2020\, SIGMOD 2022)\, and two Google Faculty Research awards (2016\, 202
 0).
DTSTART;TZID=Europe/Paris:20250416T110000
DTEND;TZID=Europe/Paris:20250416T110000
LAST-MODIFIED:20250415T155218Z
LOCATION:Aula Magna del DIAG (https://uniroma1.zoom.us/j/87937929458?pwd=NS
 tWCxSpmDhFqLkNh6Gixlx41xzGKs.1)
SUMMARY:SQL and Large Language Models: A Marriage Made in Heaven? - Prof. P
 aolo Papotti
URL;TYPE=URI:http://oba.diag.uniroma1.it/node/28700
END:VEVENT
END:VCALENDAR