BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.adass.org//adass2026//speaker//SQU88X
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-adass2026-3JPSP9@pretalx.adass.org
DTSTART;TZID=AWST:20261102T133000
DTEND;TZID=AWST:20261102T140000
DESCRIPTION:Astronomical literature is expanding at an unprecedented rate\,
  with thousands of papers added every month to preprint servers like arXiv
 .org and indexed by the NASA Astrophysics Data System (ADS). For academics
  and students\, staying current with relevant work while keeping track of 
 shifting trends therefore represents a critical challenge. I will talk abo
 ut lessons learned from developing Pathfinder\, a complement to systems li
 ke ADS that uses large language models combined with retrieval-augmented g
 eneration (RAG) to enable semantic search and question-answering across th
 e astronomy literature. I will discuss some of the unique challenges of ap
 plying NLP and LLMs to scientific publications in astronomy\, including gr
 ounding LLM responses in published literature to minimize hallucinations\,
  and leveraging embeddings to create interpretable semantic spaces for lit
 erature exploration. Drawing from Pathfinder's deployment (pfdr.app) and u
 ser feedback from the astronomy community\, I will highlight how interpret
 able intermediate representations such as semantic embeddings and citation
  graphs can lend interpretability and rigor to otherwise black-box models\
 , and help their adoption in research pipelines.
DTSTAMP:20261001T101836Z
LOCATION:Banquet Hall
SUMMARY:Using insights from the embedding spaces of large language models f
 or (astronomical) research and discovery - Kartheik Iyer
URL:https://pretalx.adass.org/adass2026/talk/3JPSP9/
END:VEVENT
END:VCALENDAR