Large Language Models Lack Understanding of Character Composition of Words

TL;DR

This paper investigates whether large language models truly understand the character-level composition of words, revealing that they perform poorly on simple character-based tasks despite their success in broader language tasks.

Contribution

The study provides a systematic analysis of LLMs' understanding of character composition, highlighting their limitations and suggesting directions for future research.

Findings

LLMs struggle with character-level tasks

Performance drops compared to token-level understanding

Identifies gaps in LLMs' linguistic comprehension

Abstract

Large language models (LLMs) have demonstrated remarkable performances on a wide range of natural language tasks. Yet, LLMs' successes have been largely restricted to tasks concerning words, sentences, or documents, and it remains questionable how much they understand the minimal units of text, namely characters. In this paper, we examine contemporary LLMs regarding their ability to understand character composition of words, and show that most of them fail to reliably carry out even the simple tasks that can be handled by humans with perfection. We analyze their behaviors with comparison to token level performances, and discuss the potential directions for future research.