Summary of What Makes Cryptic Crosswords Challenging For Llms?, by Abdelrahman Sadallah et al.
What Makes Cryptic Crosswords Challenging for LLMs?
by Abdelrahman Sadallah, Daria Kotova, Ekaterina Kochmar
First submitted to arxiv on: 12 Dec 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
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 research paper investigates why Large Language Models (LLMs) struggle to solve cryptic crosswords, a task that requires general knowledge and linguistic manipulation. The authors benchmark three popular LLMs – Gemma2, LLaMA3, and ChatGPT – and find that their performance is significantly below that of humans. To understand the reasons behind this poor performance, the paper explores the difficulties faced by these models in solving cryptic crosswords. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Solving cryptic crosswords is a challenging task even for modern language models. This paper looks at how well three popular LLMs do on this task and why they struggle to solve it better than humans. The researchers found that these models don’t do very well, and they want to know why. |
