Summary of Investigating the Potential Of Using Large Language Models For Scheduling, by Deddy Jobson et al.
Investigating the Potential of Using Large Language Models for Scheduling
by Deddy Jobson, Yilin Li
First submitted to arxiv on: 4 Jun 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper introduces the AIware Challenge at the ACM International Conference on AI-powered Software, which prompts researchers to develop AI-driven tools for optimizing conference programs through constrained optimization. Specifically, it explores the use of Large Language Models (LLMs) for program scheduling, focusing on zero-shot learning and integer programming to measure paper similarity. The study reveals that LLMs can create reasonably good first drafts of conference schedules even under zero-shot settings. Additionally, the research shows that using only titles as LLM inputs produces results closer to human categorization than using titles and abstracts with TFIDF. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about using artificial intelligence (AI) to make decisions for conferences. Right now, humans have to spend a lot of time planning out what papers to present when. This can be a big job! The researchers in this study wanted to see if AI could help make these decisions. They used special computer programs called Large Language Models (LLMs) that can understand and generate text. These models were trained to schedule papers for conferences, without needing any prior information about the papers. Surprisingly, the LLMs did a pretty good job! They also found that using just the titles of the papers was more accurate than using both titles and abstracts. |
Keywords
» Artificial intelligence » Optimization » Zero shot
