Thinking Inside the Mask: In-Place Prompting in Diffusion LLMs

Understand

Despite large language models (LLMs) have achieved remarkable success, their prefix-only prompting paradigm and sequential generation process offer limited flexibility for bidirectional information.

• Diffusion large language models (dLLMs) present new opportunities through their bidirectional attention mechanisms and iterative refinement processes, enabling more flexible in-place prompting strategies.
• We introduce ICE (In-Place Chain-of-Thought Prompting with Early Exit), a novel framework that transforms prefix-only prompting into in-place prompting specifically designed for dLLMs.
• ICE integrates in-place prompts directly within masked token positions during iterative refinement and employs a confidence-aware early exit mechanism to significantly reduce computational overhead.