A Reasoning-Based Approach to Cryptic Crossword Clue Solving

2025-06-05

AI Summary

This paper addresses the challenge of clue solving in British-style cryptic crosswords, where answers must simultaneously satisfy both a definition and a wordplay constraint. We propose the first LLM-based verifiable reasoning framework for this task. Our method employs a three-stage pipeline: (1) candidate answer generation, (2) derivation of a wordplay explanation, and (3) stepwise validation via a structured Python verifier. Crucially, we explicitly encode wordplay reasoning as executable, traceable Python operations—jointly modeling definition and wordplay pathways. Evaluated on the Cryptonite benchmark—a dataset of real cryptic clues—our approach achieves state-of-the-art accuracy, significantly outperforming prior methods. Every correct solution is accompanied by a complete, human-readable, and machine-verifiable reasoning chain. The implementation relies entirely on open-source LLM components, ensuring full transparency and reproducibility.

Technology Category

Knowledge Representation and Reasoning: Computational Complexity of ReasoningMachine Learning: Large Multimodal Models (LMMs)Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

Economics, Online Markets and Human Computation: Cost models of using LLMs in production systemsSearch and Retrieval-Augmented AI: Multilingual and cross-lingual Web searchSemantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• Solving cryptic crossword clues using LLM-based reasoning
• Generating and verifying wordplay explanations for answers
• Achieving state-of-the-art performance on Cryptonite dataset

Innovation

• LLM-based reasoning system for cryptic clues
• Hypothesizes answers and proposes wordplay explanations
• Verifier system with codified reasoning steps