A Reasoning-Based Approach to Cryptic Crossword Clue Solving
This addresses the challenge of automated cryptic crossword solving for AI and language processing enthusiasts, representing a domain-specific incremental advance.
The paper tackles the problem of solving cryptic crossword clues by developing an LLM-based reasoning system that hypothesizes answers, proposes wordplay explanations, and uses a verifier, achieving new state-of-the-art performance on the Cryptonite dataset from UK newspapers.
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.