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.

翻译：我们提出思维字符串种子（SSoT），一种新颖的LLM提示方法，用于改进概率指令跟随（PIF）。我们将PIF定义为一项任务，要求LLM从预定义选项集合中选择答案，每个选项关联特定概率，使得多次提示时生成答案的经验分布与目标分布对齐。尽管LLM在具有单一确定性答案的任务上表现出色，但在PIF任务中常常失败，表现出对需要非确定性行为的应用（如人类行为模拟、内容多样化及多人游戏）存在问题的偏差。这还会损害生成响应的多样性——测试时扩展的关键因素——导致输出坍缩到有限答案集合中。为解决此问题，我们提出SSoT，一种简单的提示方法，指示LLM首先生成随机字符串以产生足够熵。SSoT还指示LLM通过操作该字符串提取随机性来推导最终答案，从而在遵守特定约束的同时保持多样性。我们证明SSoT显著提升了LLM的PIF性能，接近伪随机数生成器的理想性能。此外，我们在NoveltyBench上的实验表明，SSoT通过增强响应多样性，其优势可扩展到开放域任务，超越闭集任务范畴。