Pith. sign in

REVIEW 2 cited by

Extracting Finite Automata from RNNs Using State Merging

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2201.12451 v3 pith:KEUAJ42F submitted 2022-01-28 cs.LG

classification cs.LG
keywords methodstateautomatafiniternnstrainedbehaviorbenchmark
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

One way to interpret the behavior of a blackbox recurrent neural network (RNN) is to extract from it a more interpretable discrete computational model, like a finite state machine, that captures its behavior. In this work, we propose a new method for extracting finite automata from RNNs inspired by the state merging paradigm from grammatical inference. We demonstrate the effectiveness of our method on the Tomita languages benchmark, where we find that it is able to extract faithful automata from RNNs trained on all languages in the benchmark. We find that extraction performance is aided by the number of data provided during the extraction process, as well as, curiously, whether the RNN model is trained for additional epochs after perfectly learning its target language. We use our method to analyze this phenomenon, finding that training beyond convergence is useful because it leads to compression of the internal state space of the RNN. This finding demonstrates how our method can be used for interpretability and analysis of trained RNN models.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. RNN Generalization to Omega-Regular Languages

    cs.LG 2025-09 conditional novelty 6.0 of 10

    RNNs trained on short ultimately periodic words achieve high out-of-distribution accuracy on most LTL-derived omega-regular language recognition tasks.

  2. Learning Model Successors

    cs.LG 2025-01 conditional novelty 6.0 of 10

    A meta-learner that transforms a model for difficulty level k into a model for level k+1 can generalize far beyond its training range, demonstrated on a bracket-matching task.

Pith tools