Showing cs.FLShow all
3 papers · 1 filter
cs.FL2024
Congruence-based Learning of Probabilistic Deterministic Finite Automata
Matías Carrasco, Franz Mayr, Sergio Yovine
This work studies the question of learning probabilistic deterministic automata from language models. For this purpose, it focuses on analyzing the relations defined on algebraic s…
cs.FL2024
Analyzing constrained LLM through PDFA-learning
Matías Carrasco, Franz Mayr, Sergio Yovine +4
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…
cs.FL2022
Towards Efficient Active Learning of PDFA
Franz Mayr, Sergio Yovine, Federico Pan +2
We propose a new active learning algorithm for PDFA based on three main aspects: a congruence over states which takes into account next-symbol probability distributions, a quantiza…