Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses

Gabriele Sarti, Tommaso Caselli, Malvina Nissim, Arianna Bisazza

Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses: 6 upvotes on Hugging Face Daily Papers, #14 of 17 papers on 2024-08-02. Day-by-day upvote history.

Rebuses are puzzles requiring constrained multi-step reasoning to identify a hidden phrase from a set of images and letters. In this work, we introduce a large collection of verbalized rebuses for the Italian language and use it to assess the rebus-solving capabilities of state-of-the-art large language models. While general-purpose systems such as LLaMA-3 and GPT-4o perform poorly on this task, ad-hoc fine-tuning seems to improve models' performance. However, we find that performance gains from training are largely motivated by memorization. Our results suggest that rebus solving remains a challenging test bed to evaluate large language models' linguistic proficiency and sequential instruction-following skills.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.