Length Controlled Generation for Black-box LLMs
This addresses a fundamental requirement for real-world applications where precise length control is needed, offering a practical solution without fine-tuning LLMs.
The paper tackles the problem of LLMs struggling to control generated text length by proposing an iterative sampling framework that integrates Metropolis-Hastings with importance sampling, achieving nearly 100% success rates on tasks like length-controlled summarization with minimal computational overhead.
Large language models (LLMs) have demonstrated impressive instruction following capabilities, while still struggling to accurately manage the length of the generated text, which is a fundamental requirement in many real-world applications. Existing length control methods involve fine-tuning the parameters of LLMs, which is inefficient and suboptimal for practical use. In this paper, we propose a novel iterative sampling framework for text length control, integrating the Metropolis-Hastings algorithm with an importance sampling acceleration strategy. This framework efficiently and reliably regulates LLMs to generate length-constrained text without modifying the underlying parameters, thereby preserving the original capabilities of LLMs. Experimental results demonstrate that our framework achieves almost 100\% success rates of length control on Llama3.1 for tasks such as length-controlled abstractive summarization and length-constrained instruction following, with minimal additional computational overhead. This also highlights the significant potential of our method for precise length control across a broader range of applications, without compromising the versatility of LLMs.