A Reasoning-Based Approach to Cryptic Crossword Clue Solving

This paper was accepted to ICML 2025 in Vancouver, Canada.

Abstract

Cryptic crossword clues are challenging language tasks for which new test sets are released daily by major newspapers on a global basis. Each cryptic clue contains both the definition of the answer to be placed in the crossword grid (in common with regular crosswords), and 'wordplay' that proves that the answer is correct (i.e. a human solver can be confident that an answer is correct without needing crossing words as confirmation). This work describes an LLM-based reasoning system built from open-licensed components that solves cryptic clues by (i) hypothesising answers; (ii) proposing wordplay explanations; and (iii) using a verifier system that operates on codified reasoning steps. Overall, this system establishes a new state-of-the-art performance on the challenging Cryptonite dataset of clues from The Times and The Telegraph newspapers in the UK. Because each proved solution is expressed in Python, interpretable wordplay reasoning for proven answers is available for inspection.

Poster Version

Explainer Video

ICML 2025 SlidesLive video will be available soon.

To get an impression of the work, please see the SlideLive verison of the ICLR Workshop Paper "Generating Code to Verify Cryptic Crossword Reasoning" :

It was also super-exciting to get a shout-out from one of the major Cryptic Crossword channels on YouTube: Cracking the Cryptic!

Link to Paper

• Direct link to paper PDF on OpenReview

And the BiBTeX entry for the arXiv version:

@misc{andrews2025reasoningbasedapproachcrypticcrossword,
  title={A Reasoning-Based Approach to Cryptic Crossword Clue Solving}, 
  author={Martin Andrews and Sam Witteveen},
  year={2025},
  eprint={2506.04824},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2506.04824}, 
}

Link to Wordplay Dataset

• Code and Sample data on GitHub

Acknowledgements

Support for this research was provided by the Google AI Developer Programs team, including access to the Gemini models and GPUs on Google Cloud Platform.