让人类直接修改AI推理过程，纠错更准更省 tokens。
Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Models
- 人类可直接编辑错误推理步骤，保留正确部分。
- 纠错成功率提升25%以上，生成tokens减少40%。
- 适合需要高精度推理的科研、教育场景。
Chain-of-Thought（CoT）推理显著提升了大语言模型处理复杂多步任务的能力。然而，当出现错误时，现有交互方式通常需重新生成回应，可能再次出错；或用户逐句标记错误，后续回复仍可能重复相同错误。为此，我们提出一种高效的人类干预机制——Deep Interaction，允许直接编辑原始响应中的错误部分，同时保留正确的推理步骤。将修正后的CoT提炼为精简提示，引导模型沿正确路径推理。实验表明，该方法在STEM任务推理中纠错成功率提升超25%，token消耗降低约40%。
原文摘要 · Abstract (English)
The emergence of Chain-of-Thought (CoT) reasoning has significantly enhanced the ability of large language models (LLMs) to tackle complex, multi-step tasks. However, when errors occur, current interaction approaches typically involve re-generating another response that may make mistakes again, or users laboriously flag the faulty step in follow-up turns that may get responses <You are right, I made a mistake here> followed by similar errors recurring. To address this issue, we propose an efficient human intervention mechanism for precisely correcting reasoning errors in LLMs, termed Deep Interaction. Our approach enables direct editing of the original response, allowing erroneous parts to be corrected while preserving accurate reasoning steps. We refine the edited CoT into a distilled prompt, which then steers the LLM along the corrected reasoning path. Experimental results show that our method achieves over a 25% improvement in correction success rate and reduces token usage by approximately 40% on STEM tasks reasoning compared to baseline approaches.
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。