BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//bsidesluxembourg-2026//talk//TGFQH9
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-bsidesluxembourg-2026-TGFQH9@pretalx.com
DTSTART;TZID=CET:20260507T154000
DTEND;TZID=CET:20260507T162000
DESCRIPTION:LLMs are often presented as a shortcut from “hundreds of find
 ings” to “actionable summary.” In reality\, getting useful and trust
 worthy output is less about a single prompt and more about understanding t
 he knobs you can turn - and what typically happens when you turn them.\n\n
 This talk uses vulnerability assessment results analysis as a concrete exa
 mple task\, but the goal is broader: a research-style exploration of the d
 esign space for LLM-assisted summarization. We’ll map the main control s
 urfaces - goal definition\, output constraints\, input shaping\, model sel
 ection\, evaluation methods\, and cost/latency budgets - and show how chan
 ging each one affects faithfulness\, specificity\, consistency\, and failu
 re modes.\n\nThe session offers a practical framework for experimenting sa
 fely: define measurable requirements\, run iterative comparisons\, and use
  structured judging to learn which combinations of knobs move you toward 
 “useful” versus “confidently wrong.” Attendees leave with a repeat
 able way to reason about tradeoffs and a set of patterns they can apply to
  other security summarization problems.
DTSTAMP:20260412T024936Z
LOCATION:IFEN room 2\, Workshops and AI Security Village  (Building D)
SUMMARY:When LLMs Summarize Security Findings: The Tradeoffs You Can’t Ig
 nore - Andrey Lukashenkov
URL:https://pretalx.com/bsidesluxembourg-2026/talk/TGFQH9/
END:VEVENT
END:VCALENDAR