What Makes Cryptic Crosswords Challenging for LLMs?
Not on the map. Why?
Abstract (arXiv)
Cryptic crosswords are puzzles that rely on general knowledge and the solver's ability to manipulate language on different levels, dealing with various types of wordplay. Previous research suggests that solving such puzzles is challenging even for modern NLP models, including Large Language Models (LLMs). However, there is little to no research on the reasons for their poor performance on this task. In this paper, we establish the benchmark results for three popular LLMs: Gemma2, LLaMA3 and ChatGPT, showing that their performance on this task is still significantly below that of humans. We also investigate why these models struggle to achieve superior performance. We release our code and introduced datasets at https://github.com/bodasadallah/decrypting-crosswords.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 29 references that are in the map. First posted on arXiv 12 Dec 2024.
Builds on
11 of 29 references.
References · 11
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
- 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
- 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,598
- 2021Curriculum Learning: A Surveycited by 259
- 2022MegaBlocks: Efficient Sparse Training with Mixture-of-Expertscited by 209
- 2023ExpertPrompting: Instructing Large Language Models to be Distinguished Expertscited by 142
- 2019Pun Generation with Surprisecited by 37
- 2019Pun-GAN: Generative Adversarial Network for Pun Generationcited by 18
- 2021Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLPcited by 16
- 2021Cryptonite: A Cryptic Crossword Benchmark for Extreme Ambiguity in Languagecited by 15
- 2024Are LLMs Good Cryptic Crossword Solvers?cited by 7
Built on by
Not cited yet.