Syntactic Control of Language Models by Posterior Inference
This addresses the challenge of ensuring clarity, stylistic consistency, or interpretability in applications requiring precise syntactic control, representing a strong specific gain.
The paper tackled the problem of controlling syntactic structure in text generated by language models, achieving an increase in F1 score from 12.31 (GPT2-large) and 35.33 (Llama3-8B) to about 93 in both cases without compromising fluency.
Controlling the syntactic structure of text generated by language models is valuable for applications requiring clarity, stylistic consistency, or interpretability, yet it remains a challenging task. In this paper, we argue that sampling algorithms based on the posterior inference can effectively enforce a target constituency structure during generation. Our approach combines sequential Monte Carlo, which estimates the posterior distribution by sampling from a proposal distribution, with a syntactic tagger that ensures that each generated token aligns with the desired syntactic structure. Our experiments with GPT2 and Llama3-8B models show that with an appropriate proposal distribution, we can improve syntactic accuracy, increasing the F1 score from $12.31$ (GPT2-large) and $35.33$ (Llama3-8B) to about $93$ in both cases without compromising the language model's fluency. These results underscore both the complexity of syntactic control and the effectiveness of sampling algorithms, offering a promising approach for applications where precise control over syntax is essential.