Efficient Guided Generation for Large Language Models
This work addresses the need for reliable and structured text generation in AI applications, offering a model-agnostic solution for enforcing domain-specific constraints.
The paper tackles the problem of guiding text generation in large language models by reformulating it as transitions in a finite-state machine, resulting in an efficient method that significantly outperforms existing solutions with minimal overhead.
In this article we show how the problem of neural text generation can be constructively reformulated in terms of transitions between the states of a finite-state machine. This framework leads to an efficient approach to guiding text generation with regular expressions and context-free grammars by allowing the construction of an index over a language model's vocabulary. The approach is model agnostic, allows one to enforce domain-specific knowledge and constraints, and enables the construction of reliable interfaces by guaranteeing the structure of the generated text. It adds little overhead to the token sequence generation process and significantly outperforms existing solutions. An implementation is provided in the open source Python library Outlines