在跨语言和多语言环境中更好地理解程序思维推理
Towards Better Understanding of Program-of-Thought Reasoning in Cross-Lingual and Multilingual Environments
AI总结：
通过分离推理与代码执行，提出评估程序思维提示的框架，发现微调显著提升多语言推理能力，且推理质量与答案准确性强相关。
摘要：
多步推理对于大型语言模型至关重要，但多语言性能仍然具有挑战性。虽然思维链提示改进了推理，但由于推理与执行的纠缠，它在非英语语言中表现不佳。程序思维提示将推理与执行分离，提供了一种有前景的替代方案，但将挑战转移到从非英语问题生成程序上。我们提出了一个框架，通过分离多语言推理与代码执行来评估程序思维，以检验（i）微调对问题-推理对齐的影响，以及（ii）推理质量如何影响答案正确性。我们的发现表明，程序思维微调显著增强了多语言推理，优于思维链微调模型。我们进一步证明了推理质量（通过代码质量衡量）与答案准确性之间的强相关性，突出了其作为测试时性能改进启发式方法的潜力。
英文摘要：
Multi-step reasoning is essential for large language models (LLMs), yet multilingual performance remains challenging. While Chain-of-Thought (CoT) prompting improves reasoning, it struggles with non-English languages due to the entanglement of reasoning and execution. Program-of-Thought (PoT) prompting separates reasoning from execution, offering a promising alternative but shifting the challenge to generating programs from non-English questions. We propose a framework to evaluate PoT by separating multilingual reasoning from code execution to examine (i) the impact of fine-tuning on question-reasoning alignment and (ii) how reasoning quality affects answer correctness. Our findings demonstrate that PoT fine-tuning substantially enhances multilingual reasoning, outperforming CoT fine-tuned models. We further demonstrate a strong correlation between reasoning quality (measured through code quality) and answer accuracy, highlighting its potential as a test-time performance improvement heuristic.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
