字符串思维种子：用于大语言模型的提示方法以实现分布忠实和多样化生成
String Seed of Thought: Prompting LLMs for Distribution-Faithful and Diverse Generation
AI总结：
SSoT通过引入随机字符串生成和提取机制，提升大语言模型在分布忠实和多样化生成任务中的性能。
摘要：
我们介绍了字符串思维种子（SSoT），一种新颖的提示方法，用于大语言模型（LLMs），以提高概率指令遵循（PIF）性能。我们将PIF定义为一项任务，要求LLM从预定义的一组选项中选择答案，每个选项关联特定概率，使得在多次提示时生成答案的实证分布与目标分布一致。尽管LLM在单个确定性答案的任务上表现出色，但在PIF任务上却经常表现不佳，表现出对需要非确定性行为的应用（如人类行为模拟、内容多样化和多人游戏）具有问题性的偏差。此外，它还会损害生成响应的多样性，这是测试时间扩展的关键因素，因为它会使输出集中于有限的答案集合中。为了解决这个问题，我们提出了SSoT，一种简单的提示方法，该方法指导LLM首先输出一个随机字符串以生成足够的熵。SSoT还指导LLM通过操纵该字符串来提取随机性，从而推导出最终答案，从而在遵守特定约束的同时保持多样性。我们证明SSoT显著提高了LLM的PIF性能，接近伪随机数生成器的理想性能。此外，我们的NoveltyBench实验表明，SSoT的好处不仅限于封闭集任务，还通过增强响应多样性扩展到了开放式任务。
英文摘要：
We introduce String Seed of Thought (SSoT), a novel prompting method for LLMs that improves Probabilistic Instruction Following (PIF). We define PIF as a task requiring an LLM to select its answer from a predefined set of options, each associated with a specific probability, such that the empirical distribution of the generated answers aligns with the target distribution when prompted multiple times. While LLMs excel at tasks with single, deterministic answers, they often fail at PIF, exhibiting biases problematic for applications requiring non-deterministic behaviors, such as human-behavior simulation, content diversification, and multiplayer games. It also harms the diversity of generated responses, a crucial factor in test-time scaling, by causing the outputs to collapse into a limited set of answers. To address this, we propose SSoT, a simple prompting method that instructs an LLM to first output a random string to generate sufficient entropy. SSoT also instructs the LLM to extract randomness by manipulating this string to derive a final answer, thereby preserving diversity while adhering to specific constraints. We demonstrate that SSoT significantly improves the PIF performance of LLMs, approaching the ideal performance of a pseudo-random number generator. Furthermore, our experiments on NoveltyBench show SSoT's benefits extend beyond closed-set tasks to open-ended tasks by enhancing response diversity.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
