Proving that Cryptic Crossword Clue Answers are Correct
This addresses the challenge of automated verification for cryptic crossword clues, which are daily cognitive tasks in international newspapers, but the approach is incremental as it builds on an existing framework.
The paper tackled the problem of verifying the correctness of cryptic crossword clue answers by distinguishing between correct and almost-correct answers based on whether the wordplay 'works', using an existing framework with Python proofs generated by an LLM.
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'.