让大模型先说出意图，再生成内容，提升推理与表达质量。
SWI: Speaking with Intent in Large Language Models
- 大模型生成答案前先明确自身意图，作为高层规划指导后续输出。
- 在摘要、问答和数学推理任务中，带意图的生成效果显著优于直接生成。
- 人类评估证实意图清晰可读，有助于理解模型决策过程。
意图通常被明确地制定和规划，是沟通与问题解决的认知框架。本文提出在大型语言模型中引入‘有意识说话’（Speaking with Intent, SWI），即显式生成意图，以捕捉模型的内在意图，并为后续分析与行动提供高层规划。通过模拟人类刻意且有目的性的思维过程，假设SWI能增强大模型的推理能力和生成质量。在文本摘要、多任务问答及数学推理基准上的大量实验一致证明，相较于无显式意图的直接生成，SWI在有效性与泛化性方面表现更优。进一步分析验证了其在不同实验设置下的普适性。此外，人工评估确认了SWI所生成意图的连贯性、有效性和可解释性。这些成果表明，通过引入显式意图，为提升大模型的生成与推理能力开辟了基于认知理念的新路径。
原文摘要 · Abstract (English)
Intent, typically clearly formulated and planned, functions as a cognitive framework for communication and problem-solving. This paper introduces the concept of Speaking with Intent (SWI) in large language models (LLMs), where the explicitly generated intent encapsulates the model's underlying intention and provides high-level planning to guide subsequent analysis and action. By emulating deliberate and purposeful thoughts in the human mind, SWI is hypothesized to enhance the reasoning capabilities and generation quality of LLMs. Extensive experiments on text summarization, multi-task question answering, and mathematical reasoning benchmarks consistently demonstrate the effectiveness and generalizability of Speaking with Intent over direct generation without explicit intent. Further analysis corroborates the generalizability of SWI under different experimental settings. Moreover, human evaluations verify the coherence, effectiveness, and interpretability of the intent produced by SWI. The promising results in enhancing LLMs with explicit intents pave a new avenue for boosting LLMs' generation and reasoning abilities with cognitive notions.
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。