Exchange of Perspective Prompting Enhances Reasoning in Large Language Models
On the map: LLM reasoning → Reasoning benchmarks and evaluation
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 21 of its 53 references that are in the map. First posted on arXiv 4 Jun 2025.
Builds on
21 of 53 references.
Closest ancestors · 3
Same direction, newest first
- 2023Re-Reading Improves Reasoning in Large Language Models12 Sep
- 2023Cumulative Reasoning with Large Language Models8 Aug
- 2021Show Your Work: Scratchpads for Intermediate Computation with Language Models30 Nov
Other references · 18
- 2023GPT-4 Technical Reportcited by 18,396
- 2021Training Verifiers to Solve Math Word Problemscited by 10,109
- 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
- 2024Qwen2 Technical Reportcited by 2,120
- 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,202
- 2024Training Language Models to Self-Correct via Reinforcement Learningcited by 426
- 2022BlenderBot 3: a deployed conversational agent that continually learns to responsibly engagecited by 198
- 2023The Capacity for Moral Self-Correction in Large Language Modelscited by 173
- 2024Recursive Introspection: Teaching Language Model Agents How to Self-Improvecited by 165
- 2023Progressive-Hint Prompting Improves Reasoning in Large Language Modelscited by 147
- 2024LLM Critics Help Catch LLM Bugscited by 147
- 2023Can Large Language Models Really Improve by Self-critiquing Their Own Plans?cited by 108
6 more
- 2023Learning From Mistakes Makes LLM Better Reasonercited by 101
- 2023Shepherd: A Critic for Language Model Generationcited by 97
- 2023GPT-4 Doesn't Know It's Wrong: An Analysis of Iterative Prompting for Reasoning Problemscited by 89
- 2023Skills-in-Context Prompting: Unlocking Compositionality in Large Language Modelscited by 33
- 2024Zero-Shot Chain-of-Thought Reasoning Guided by Evolutionary Algorithms in Large Language Modelscited by 15
- 2024Large Language Models are Contrastive Reasonerscited by 11
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Perspective Transition of Large Language Models for Solving Subjective Tasks
- 2025Probing Large Language Models in Reasoning and Translating Complex Linguistic Puzzles
- 2023Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication
- 2023Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting
- 2025Thinking Before You Speak: A Proactive Test-time Scaling Approach
- 2024Think Beyond Size: Adaptive Prompting for More Effective Reasoning
- 2025When Language Shapes Thought: Cross-Lingual Transfer of Factual Knowledge in Question Answering
- 2025Reasoning Capabilities and Invariability of Large Language Models