# Proving that Cryptic Crossword Clue Answers are Correct

arXiv: https://arxiv.org/abs/2407.08824 · HTML: https://mlsanity.com/paper/2407.08824/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 17 references that are in the map.
- First posted on arXiv 11 Jul 2024.

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

- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs](https://mlsanity.com/paper/2210.12283/) (2022)
- [Advances in Pre-Training Distributed Word Representations](https://mlsanity.com/paper/1712.09405/) (2017)
- [Can Large Language Models Reason and Plan?](https://mlsanity.com/paper/2403.04121/) (2024)
- [Cryptonite: A Cryptic Crossword Benchmark for Extreme Ambiguity in Language](https://mlsanity.com/paper/2103.01242/) (2021)

## Abstract (arXiv)

Cryptic crossword clues are challenging cognitive tasks, for which new test sets are released on a daily basis by multiple international newspapers. 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 to confirm it). Using an existing cryptic wordplay proving framework (operating on Python proofs created by an LLM), we show that it is possible to distinguish between correct answers and almost-correct ones based upon whether the wordplay `works'.