研究：问题改写何时提升 LLM 解题准确率
Same Task, Different Statement: When and How Reformulation Helps LLM Problem Solving
做了实验才知道：让模型先重述题目不是万能的。这篇论文测了 8 个模型、8 个基准，给出三种改写方式和固定规则，规则化改写能涨 11.0%，乱改反而掉 5.6%。写提示词的人应该看看什么时候改写才有用。
一篇 arXiv 论文系统研究了让模型先改写题目再解题的效果。作者定义了三种改写：Decomposition（显式拆分隐含子目标）、Typed Reformulation（把任务转换到更合适的求解框架）、Concept Reduction（剥离表面细节、暴露任务结构），并在 8 个数学、逻辑和代码基准上测试了 8 个模型，统一使用相同的 chain-of-thought 求解提示。
结果显示改写的效果依赖题型：一个事后挑选最优改写的 oracle 平均可将准确率提升 27.6%，但没有任何单一改写对所有题目有效，选错改写反而降低表现。不同改写方式各有适配的题型，存在清晰规律。
更有实用价值的是，从一个问题集合学到的简单固定规则可以把部分收益迁移到新问题上：在其选择改写的题目上提升 11.0%，而盲目改写在相近比例的题目上反而损失 5.6%。结论是改写不是通用解题手段，关键在于何时改写以及如何改写。
Same Task, Different Statement: When and How Reformulation Helps LLM Problem Solving
When people face a hard problem, they often restate it in a clearer way before solving it. We study whether the same habit helps large language models by rewriting the statement of a problem. A legal rewrite must keep the meaning, the constraints, and the correct answer unchanged. We test three kinds of rewrites. Decomposition makes hidden subgoals explicit. Typed Reformulation casts the task into a more suitable solving frame. Concept Reduction removes surface detail and exposes the task structure. We evaluate them on eight math, logic, and code benchmarks with eight models, all under the same chain-of-thought solving prompt. The effect is large but depends on the problem type. An oracle that picks the best rewrite after the fact raises accuracy by +27.6% on average. Yet no single rewrite helps every problem, and a mismatched rewrite can hurt. Still, the effect follows clear patterns. Each kind of rewrite fits certain problem types. A simple fixed rule learned from one set of problems transfers part of the gain to new problems. It gains +11.0% on the problems it chooses to rewrite, while blind rewriting loses 5.6% on a similar share of problems. Rewriting is therefore not a universal way to solve problems. The question is when and how to rewrite.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include chain-of-thought, 提示词工程, 推理模型, LLM.
Source attribution: curated from arXiv cs.AI (@Wentao Zhang, Xiaoyu Zhang, Chengwei Liu, Yutao Hu, Tao Zhang, Junsheng Wu, Hongping Gan, Yang Liu).
