# Analyzing constrained LLM through PDFA-learning

arXiv: https://arxiv.org/abs/2406.08269 · HTML: https://mlsanity.com/paper/2406.08269/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 14 references that are in the map.
- First posted on arXiv 12 Jun 2024.

## Builds on (most cited first, 4 of 4)

- [Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples](https://mlsanity.com/paper/1711.09576/) (2017)
- [Validating Large Language Models with ReLM](https://mlsanity.com/paper/2211.15458/) (2022)
- [A Measure-Theoretic Characterization of Tight Language Models](https://mlsanity.com/paper/2212.10502/) (2022)
- [An Empirical Evaluation of Rule Extraction from Recurrent Neural Networks](https://mlsanity.com/paper/1709.10380/) (2017)

## Built on by (most cited first, 1 of 1)

- [Congruence-based Learning of Probabilistic Deterministic Finite Automata](https://mlsanity.com/paper/2412.09760/) (2024)

## Abstract (arXiv)

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.