kernel_entropy.pipeline

KLE Pipeline - end-to-end Kernel Language Entropy computation.

Single function that orchestrates: Generation -> NLI -> KLE calculation

Functions

compute_kle(prompt[, n_generations, ...])

Compute Kernel Language Entropy for a prompt.
kernel_entropy.pipeline.compute_kle(prompt: str, n_generations: int = 10, temperature: float = 0.98, lengthscale_t: float = 1.0, verbose: bool = False) → float[source]

Compute Kernel Language Entropy for a prompt.

Pipeline:

  1. Generate N responses via PoE (pure generation, no uncertainty head)

  2. Compute pairwise NLI similarity matrix W

  3. Calculate Von Neumann Entropy from W

Parameters:

  • prompt – Input prompt for generation

  • n_generations – Number of responses to generate (default: 10)

  • temperature – Generation temperature (default: 0.98)

  • lengthscale_t – Heat kernel lengthscale (default: 1.0)

  • verbose – Print each response after generation (default: False)

Returns:

Von Neumann Entropy (float). Higher = more semantic uncertainty.