Artificial Intelligence #positional bias#in-context learning
Where to Place the Query? Unveiling and Mitigating Positional Bias in Diffusion LLMs via Decoding Dynamics
Researchers uncover that query placement is a first-order variable in diffusion large language models (dLLMs), affecting output quality as much as example semantics. They propose a training-free adaptive routing strategy, Auto-ICL, and a novel metric Average Confidence to mitigate positional bias without ground-truth labels.
Jun 20, 2026 1 source
