用后验推断方法让大模型生成语法更规范的文本
Syntactic Control of Language Models by Posterior Inference
- 通过后验推断与语法标签器结合，控制生成文本的句法结构
- GPT2和Llama3-8B的句法准确率F1从不足40提升至约93
- 适合需要语法严谨性的场景，如技术写作或可解释性生成
控制语言模型生成文本的句法结构在需要清晰性、风格一致或可解释性的应用中具有重要价值，但仍是挑战。本文提出基于后验推断的采样算法，可在生成过程中有效施加目标成分结构。方法结合序列蒙特卡洛（Sequential Monte Carlo），通过从提议分布采样估计后验分布，并利用语法标签器确保每个生成词符与目标句法结构对齐。在GPT2-large和Llama3-8B模型上的实验表明，采用合适的提议分布后，句法准确率F1得分从12.31（GPT2-large）和35.33（Llama3-8B）分别提升至约93，且未牺牲语言模型的流畅性。结果凸显了句法控制的复杂性与采样算法的有效性，为需要精确句法控制的应用提供了有前景的解决方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。