让大模型换角度看问题，显著提升推理能力
Exchange of Perspective Prompting Enhances Reasoning in Large Language Models
- 通过切换问题定义视角，打破固定思维模式
- 在AQuA等8个基准上平均提升3.6%~7.7%准确率
- 适合需要深度推理的数学与逻辑任务
大语言模型在自然语言处理任务中取得显著进展，但其表现常受限于对问题的理解深度。为此，本文提出一种名为视角交换（EoP）的新框架，通过在不同问题定义间切换视角，打破单一表述带来的思维定式。我们在8个基准上进行了广泛而全面的实验。结果表明，EoP能显著提升性能：相比非交换基线方法PHP，使用GPT-3.5-Turbo时，AQuA准确率从60.6%提升至64.2%（+3.6%）；而使用GPT-4时，Math基准整体准确率从53.9%提升至61.6%（+7.7%），OlympiadBench Maths从43.5%提升至47.0%（+3.5%），均采用Qwen-2.5-72b作为辅助模型。
原文摘要 · Abstract (English)
Large language models (LLMs) have made significant advancements in addressing diverse natural language processing (NLP) tasks. However, their performance is often limited by inherent comprehension of problems. To address this limitation, we propose Exchange-of-Perspective (EoP), a novel framework designed to exchange perspectives across different definitions of problem, so that it can break the fixed mindset from any particular formulation of the question. We conducted extensive and comprehensive experiments on 8 benchmarks. The results show that EoP can significantly improve performance. For instance, compared to the non-commutative baseline PHP, with GPT-3.5-Turbo and EoP, we observe a 3.6% improvement on AQuA (60.6% to 64.2%), while GPT-4-powered EoP demonstrates a 7.7% overall accuracy enhancement on Math (53.9% to 61.6%) and a 3.5% improvement on OlympiadBench Maths (43.5% to 47.0%) when using Qwen-2.5-72b.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。