output distribution
This refers to the probabilistic distribution of the possible outcomes generated by a model given a specific input. Understanding the output distribution enables predictions about the uncertainty and variability of the model's predictions.
- Approximately Aligned Decoding
- Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language Models
- Decoupled Entropy Minimization
- Distribution-Aware Tensor Decomposition for Compression of Convolutional Neural Networks
- Majority of the Bests: Improving Best-of-N via Bootstrapping
- RAST: Reasoning Activation in LLMs via Small-model Transfer
- Remarkable Robustness of LLMs: Stages of Inference?
- The Mirage of Performance Gains: Why Contrastive Decoding Fails to Mitigate Object Hallucinations in MLLMs?