Word Form Matters: LLMs' Semantic Reconstruction under Typoglycemia
This work addresses the problem of understanding LLM mechanisms for language processing, which could help enhance their performance by incorporating human-like context-aware strategies, though it is incremental in nature.
The researchers investigated how large language models (LLMs) reconstruct meaning from scrambled words (typoglycemia), finding that word form is the core factor in semantic reconstruction, with LLMs using specialized attention heads to process this information. They proposed SemRecScore to quantify semantic reconstruction and validated its effectiveness.
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.