# Solving and Generating NPR Sunday Puzzles with Large Language Models

arXiv: https://arxiv.org/abs/2306.12255 · HTML: https://mlsanity.com/paper/2306.12255/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 9 references that are in the map.
- First posted on arXiv 21 Jun 2023.

## Builds on (most cited first, 5 of 5)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Quizbowl: The Case for Incremental Question Answering](https://mlsanity.com/paper/1904.04792/) (2019)
- [Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLP](https://mlsanity.com/paper/2104.08620/) (2021)

## Built on by (most cited first, 7 of 7)

- [Stable LM 2 1.6B Technical Report](https://mlsanity.com/paper/2402.17834/) (2024)
- [Step-by-Step Reasoning to Solve Grid Puzzles: Where do LLMs Falter?](https://mlsanity.com/paper/2407.14790/) (2024)
- [Missed Connections: Lateral Thinking Puzzles for Large Language Models](https://mlsanity.com/paper/2404.11730/) (2024)
- [REBUS: A Robust Evaluation Benchmark of Understanding Symbols](https://mlsanity.com/paper/2401.05604/) (2024)
- [Connecting the Dots: Evaluating Abstract Reasoning Capabilities of LLMs Using the New York Times Connections Word Game](https://mlsanity.com/paper/2406.11012/) (2024)
- [LLMs as Method Actors: A Model for Prompt Engineering and Architecture](https://mlsanity.com/paper/2411.05778/) (2024)
- [Do multimodal models imagine electric sheep?](https://mlsanity.com/paper/2605.09693/) (2026)

## Abstract (arXiv)

We explore the ability of large language models to solve and generate puzzles from the NPR Sunday Puzzle game show using PUZZLEQA, a dataset comprising 15 years of on-air puzzles. We evaluate four large language models using PUZZLEQA, in both multiple choice and free response formats, and explore two prompt engineering techniques to improve free response performance: chain-of-thought reasoning and prompt summarization. We find that state-of-the-art large language models can solve many PUZZLEQA puzzles: the best model, GPT-3.5, achieves 50.2% loose accuracy. However, in our few-shot puzzle generation experiment, we find no evidence that models can generate puzzles: GPT-3.5 generates puzzles with answers that do not conform to the generated rules. Puzzle generation remains a challenging task for future work.