Think in Sentences: Explicit Sentence Boundaries Enhance Language Model's Capabilities

arXiv:2604.10135v1 Announce Type: cross Abstract: Researchers have explored different ways to improve large language models (LLMs)' capabilities via dummy token insertion in contexts. However, existing works focus solely on the dummy tokens themselves, but fail to leverage the inherent sentence-level structure of natural language. This is a critical oversight, as LLMs acquire linguistic capabilities through exposure to human-generated texts, which are inherently structured at the sentence level.