Automata-based constraints for language model decoding

Terry Koo, Frederick Liu, Luheng He

Research Area: Inference algorithms for LMs, LMs with tools and code

Keywords: finite state automaton, finite state transducer, pushdown automaton, language model, constrained decoding

TL;DR: Using automata theory to provide efficient, comprehensive, closed-form solutions for LM decoding constraints.

Abstract:

Language models (LMs) are often expected to generate strings in some formal language; for example, structured data, API calls, or code snippets.
Although LMs can be tuned to improve their adherence to formal syntax, this does not *guarantee* conformance, especially with smaller LMs suitable for large-scale deployment.
In addition, tuning requires significant resources, making it impractical for uncommon or task-specific formats.
To prevent downstream parsing errors we would ideally *constrain* the LM to only produce valid output, but this is severely complicated by tokenization, which is typically both ambiguous and misaligned with the formal grammar.
We solve these issues through the application of automata theory, deriving an efficient closed-form solution for the *regular languages*, a broad class of formal languages with many practical applications, including API calls or schema-guided JSON and YAML.
We also discuss pragmatic extensions for coping with the issue of high branching factor, and extend our techniques to *deterministic context-free languages*, which similarly admit an efficient closed-form solution.
Previous work on this topic (Willard and Louf, 2023) layers bespoke solutions onto automata, leading to problems with speed, correctness, and extensibility.
Instead, we reformulate the entire task in terms of automata so we can leverage well-studied and well-optimized algorithms.
Our system compiles constraints ~7,000x faster, is provably correct, and can be extended in a modular fashion.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 771