arXiv cs.AI· Wentao Zhang, Xiaoyu Zhang, Chengwei Liu, Yutao Hu, Tao Zhang, Junsheng Wu, Hongping Gan, Yang Liu·· 1 小时前AI 评分54
研究探讨改写题目表述何时能提升大语言模型解题能力
Same Task, Different Statement: When and How Reformulation Helps LLM Problem Solving
AI 导读
arXiv 论文 arXiv:2611.14997 研究改写题目表述对大语言模型解题的帮助，测试分解、类型化改写和概念精简三种方式，覆盖 8 个数学、逻辑与代码基准和 8 个模型。事后选择最优改写的 oracle 平均提升 +27.6%，但没有一种改写对所有问题有效，错误改写反而有害；从一类问题学到的固定规则在所选问题上获得 +11.0%，而盲目改写在类似比例的问题上损失 5.6%。
正文 · 原文
Abstract: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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.14997 [cs.AI] |
| (or arXiv:2611.14997v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.14997 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Wentao Zhang [view email]
[v1]
Wed, 11 Nov 2026 03:55:59 UTC (1,373 KB)
来源：arXiv cs.AI · arxiv.org