Papers › Analyzing constrained LLM through PDFA-learning

Analyzing constrained LLM through PDFA-learning

12 Jun 2024arXiv:2406.08269archive 2025-07-28

Matías Carrasco, Franz Mayr, Sergio Yovine, Johny Kidd, Martín Iturbide, Juan Pedro da Silva, Alejo Garat

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.

PaperPDFCode

Code

neuralchecker/analyzing_constrained_llm_through_pdfa_learning officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language ModelingLanguage ModellingText Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections