FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation

Excerpt

arXiv:2609.27657v1 Announce Type: cross Abstract: Solutions based on large language models (LLMs) often rely on temperature sampling to improve accuracy and stability by aggregating multiple samples from the completion distribution. However, this memoryless approach is inherently suboptimal: because it lacks awareness of prior generations and their evaluations, it produces an increasing proportion of semantically duplicate answers as more samples are drawn, leading to diminishing returns. To add