Investigating the Potential of Using Large Language Models for Scheduling
This addresses the challenge of automated scheduling for conference organizers, but it is incremental as it builds on existing LLM and optimization techniques.
The study tackled the problem of optimizing conference program scheduling by using Large Language Models (LLMs) in a zero-shot setting, finding that LLMs with only titles as inputs produced schedules closer to human categorization than traditional TFIDF methods with titles and abstracts.
The inaugural ACM International Conference on AI-powered Software introduced the AIware Challenge, prompting researchers to explore AI-driven tools for optimizing conference programs through constrained optimization. We investigate the use of Large Language Models (LLMs) for program scheduling, focusing on zero-shot learning and integer programming to measure paper similarity. Our study reveals that LLMs, even under zero-shot settings, create reasonably good first drafts of conference schedules. When clustering papers, using only titles as LLM inputs produces results closer to human categorization than using titles and abstracts with TFIDF. The code has been made publicly available.