BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.adass.org//adass2026//speaker//B3RFBJ
BEGIN:VTIMEZONE
TZID:AWST
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1;UNTIL=20051231T160000Z
TZNAME:AWST
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
END:STANDARD
BEGIN:STANDARD
DTSTART:20070325T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:AWST
TZOFFSETFROM:+0900
TZOFFSETTO:+0800
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20071028T030000
RRULE:FREQ=YEARLY;BYDAY=4SU;BYMONTH=10;UNTIL=20081025T190000Z
TZNAME:AWDT
TZOFFSETFROM:+0800
TZOFFSETTO:+0900
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-adass2026-WUYEGC@pretalx.adass.org
DTSTART;TZID=AWST:20261102T161500
DTEND;TZID=AWST:20261102T163000
DESCRIPTION:Generating database queries from natural language remains a cha
 llenging task\, particularly in specialized scientific domains. In this wo
 rk\, we study natural language to Astronomical Data Query Language (ADQL) 
 generation using large language models (LLMs). We curate a high-quality da
 taset of natural language–ADQL pairs through an LLM-assisted filtering a
 nd validation pipeline and use it to fine-tune models of varying sizes and
  capabilities. To enable systematic evaluation\, we construct an expert-an
 notated benchmark of queries for the Gaia mission\, spanning a range of qu
 ery complexities\, from simple retrieval tasks to complex joins and aggreg
 ations. Finally\, we compare fine-tuned models against retrieval-augmented
  generation (RAG) approaches\, analyzing their effectiveness in terms of q
 uery correctness and robustness. Our results provide insights into the rel
 ative strengths of fine-tuning and retrieval augmentation for domain-speci
 fic scientific query generation.
DTSTAMP:20261001T101700Z
LOCATION:Banquet Hall
SUMMARY:ADQL generation using LLMs - Sandor Kruk
URL:https://pretalx.adass.org/adass2026/talk/WUYEGC/
END:VEVENT
END:VCALENDAR