CUTE: Measuring LLMs' Understanding of Their Tokens

Autor:	Edman, Lukas, Schmid, Helmut, Fraser, Alexander
Rok vydání:	2024
Předmět:	Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	Large Language Models (LLMs) show remarkable performance on a wide variety of tasks. Most LLMs split text into multi-character tokens and process them as atomic units without direct access to individual characters. This raises the question: To what extent can LLMs learn orthographic information? To answer this, we propose a new benchmark, CUTE, which features a collection of tasks designed to test the orthographic knowledge of LLMs. We evaluate popular LLMs on CUTE, finding that most of them seem to know the spelling of their tokens, yet fail to use this information effectively to manipulate text, calling into question how much of this knowledge is generalizable. Comment: Accepted to EMNLP 2024 main conference
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2409.15452 Zobrazit plný text záznamu View this record from Arxiv