Analyzing constrained LLM through PDFA-learning
Not on the map. Why?
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 4 of its 14 references that are in the map. First posted on arXiv 12 Jun 2024.
Builds on
4 of 14 references.
References · 4
- 2017Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamplescited by 66
- 2022Validating Large Language Models with ReLMcited by 33
- 2022A Measure-Theoretic Characterization of Tight Language Modelscited by 32
- 2017An Empirical Evaluation of Rule Extraction from Recurrent Neural Networkscited by 21
Built on by
Citing papers per year: 2024: 1.
1 paper.