Analyzing constrained LLM through PDFA-learning

Code

• github.com/neuralchecker/analyzing_constrained_llm_through_pdfa_learning
  OfficialIn papernone★ 0

Abstract

We define a congruence that copes with null next-symbol probabilities that arise when the output of a language model is constrained by some means during text generation. We develop an algorithm for efficiently learning the quotient with respect to this congruence and evaluate it on case studies for analyzing statistical properties of LLM.

Tasks

Reproductions