Exchange of Perspective Prompting Enhances Reasoning in Large Language Models
This addresses the problem of fixed mindsets in LLMs for NLP tasks, offering incremental improvements in reasoning performance.
The paper tackled the limitation of large language models in problem comprehension by proposing the Exchange-of-Perspective (EoP) framework, which improved performance on benchmarks, such as a 3.6% increase on AQuA with GPT-3.5-Turbo and a 7.7% gain on Math with GPT-4.
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.