Word Form Matters: LLMs' Semantic Reconstruction under Typoglycemia

Understand

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.