BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250626T233528Z
LOCATION:B302-B305
DTSTART;TZID=America/New_York:20241120T100000
DTEND;TZID=America/New_York:20241120T170000
UID:submissions.supercomputing.org_SC24_sess533_post203@linklings.com
SUMMARY:Large-Scale Randomized Program Generation with Large Language Mode
 ls​
DESCRIPTION:Tyler Lam (University of California, Berkeley) and Lingda Li (
 Brookhaven National Laboratory)\n\nLarge, diverse datasets of executable p
 rograms are required for training and running machine learning models to f
 ind insights in program performance. While many open-source code repositor
 ies exist freely on popular software development websites such as GitHub, 
 the safety and executability of such programs cannot be guaranteed. To bri
 dge this gap, this study proposes LLMRPG (Large Language Model-based Rando
 mized Program Generator), a program generator that harnesses open-source l
 arge language models (LLMs) fine-tuned for code generation to generate err
 or-free, executable, and human-like programs on demand. The performance of
  LLMRPG was evaluated across popular open-source LLMs using heuristics suc
 h as the semantic similarity between programs, and the proportion of compi
 lable and executable programs generated by LLMRPG. Analysis on the program
 s generated by LLMRPG demonstrates that these programs have satisfactory c
 ompilability and executability, as well as high diversity.\n\nRegistration
  Category: Tech Program Reg Pass, Exhibits Reg Pass\n\nSession Chairs: Aye
 sha Afzal (Friedrich-Alexander University, Erlangen-Nuremberg; Erlangen Na
 tional High Performance Computing Center); Sally Ellingson (University of 
 Kentucky); and Alan Sussman (University of Maryland)\n\n
END:VEVENT
END:VCALENDAR