用多维提示链让小模型对话更自然流畅。
Multi-Dimensional Prompt Chaining to Improve Open-Domain Dialogue Generation
- 设计自然、连贯、有趣三维度提示链，提升对话质量。
- 小模型响应多样性提升29%，连贯性提升28%。
- 适合资源有限但需高质量对话的场景使用。
小语言模型（SLMs）在部署上优势明显，但在开放域对话中常难以媲美大模型的表现。本文提出一种多维提示链框架，融合自然度、连贯性与吸引力三个维度，以增强开放域对话的人类化特征。将该框架应用于TinyLlama和Llama-2-7B两个SLMs，与更大模型如Llama-2-70B和GPT-3.5 Turbo进行对比。通过自动评估与人工评价，检验其在多样性、上下文连贯性及整体质量上的表现。结果表明，完整框架使响应多样性最高提升29%，上下文连贯性最高提升28%，自然度与吸引力亦提升至多29%。值得注意的是，Llama-2-7B的表现可媲美显著更大的模型，包括Llama-2-70B和GPT-3.5 Turbo。研究证明，精心设计的提示策略为提升小模型开放域对话质量提供了一条高效且资源节约的路径。
原文摘要 · Abstract (English)
Small language models (SLMs) offer significant deployment advantages but often struggle to match the dialogue quality of larger models in open-domain settings. In this paper, we propose a multi-dimensional prompt-chaining framework that integrates Naturalness, Coherence, and Engagingness dimensions to enhance human-likeness in open-domain dialogue generation. We apply the framework to two SLMs, TinyLlama and Llama-2-7B, and benchmark their performance against responses generated by substantially larger models, including Llama-2-70B and GPT-3.5 Turbo. We then employ automatic and human evaluation to assess the responses based on diversity, contextual coherence, as well as overall quality. Results show that the full framework improves response diversity by up to 29%, contextual coherence by up to 28%, and engagingness as well as naturalness by up to 29%. Notably, Llama-2-7B achieves performance comparable to substantially larger models, including Llama-2-70B and GPT-3.5 Turbo. Overall, the findings demonstrate that carefully designed prompt-based strategies provide an effective and resource-efficient pathway to improving open-domain dialogue quality in SLMs.
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。