詞形至關重要：大語言模型在字母亂序下的語義重建

Word Form Matters: LLMs' Semantic Reconstruction under Typoglycemia

March 3, 2025

作者: Chenxi Wang, Tianle Gu, Zhongyu Wei, Lang Gao, Zirui Song, Xiuying Chen

cs.AI

摘要

人類讀者能夠高效地理解打亂順序的單詞，這一現象被稱為「字母位置錯亂症」（Typoglycemia），主要依賴於單詞形式；若僅憑單詞形式不足以理解，他們會進一步利用上下文線索進行解讀。雖然先進的大型語言模型（LLMs）展現出相似的能力，但其背後的機制仍不明確。為探究此問題，我們進行了控制實驗，分析單詞形式和上下文信息在語義重建中的作用，並檢視LLM的注意力模式。具體而言，我們首先提出了SemRecScore，這是一個可靠的指標，用於量化語義重建的程度，並驗證了其有效性。利用這一指標，我們研究了單詞形式和上下文信息如何影響LLMs的語義重建能力，發現單詞形式是這一過程的核心因素。此外，我們分析了LLMs如何利用單詞形式，發現它們依賴於專門的注意力頭來提取和處理單詞形式信息，且這一機制在不同程度的單詞打亂下保持穩定。LLMs主要專注於單詞形式的固定注意力模式與人類讀者在平衡單詞形式和上下文信息時的適應性策略之間的區別，為通過融入類人的、上下文感知的機制來提升LLM性能提供了洞見。

English

Human readers can efficiently comprehend scrambled words, a phenomenon known as Typoglycemia, primarily by relying on word form; if word form alone is insufficient, they further utilize contextual cues for interpretation. While advanced large language models (LLMs) exhibit similar abilities, the underlying mechanisms remain unclear. To investigate this, we conduct controlled experiments to analyze the roles of word form and contextual information in semantic reconstruction and examine LLM attention patterns. Specifically, we first propose SemRecScore, a reliable metric to quantify the degree of semantic reconstruction, and validate its effectiveness. Using this metric, we study how word form and contextual information influence LLMs' semantic reconstruction ability, identifying word form as the core factor in this process. Furthermore, we analyze how LLMs utilize word form and find that they rely on specialized attention heads to extract and process word form information, with this mechanism remaining stable across varying levels of word scrambling. This distinction between LLMs' fixed attention patterns primarily focused on word form and human readers' adaptive strategy in balancing word form and contextual information provides insights into enhancing LLM performance by incorporating human-like, context-aware mechanisms.