DialogueForge：人机对话的LLM模拟框架
DialogueForge: LLM Simulation of Human-Chatbot Dialogue
AI总结：
本文提出DialogueForge框架，利用多种LLM模拟人机对话，并通过微调提升小模型生成逼真对话的能力，实验表明大模型更优而小模型经微调后性能显著提升。
摘要：
收集人机对话通常需要大量人工且耗时，这限制并挑战了对话式人工智能的研究。本文提出DialogueForge——一个用于生成人机风格AI模拟对话的框架。为初始化每段生成对话，DialogueForge使用从真实人机交互中提取的种子提示。我们测试了多种LLM来模拟人类聊天机器人用户，涵盖最先进的专有模型到小规模开源LLM，并生成针对特定任务定制的多轮对话。此外，我们探索微调技术以增强较小模型生成难以区分的人类风格对话的能力。我们使用UniEval和GTEval评估协议评估模拟对话的质量并比较不同模型。实验表明，大型专有模型（如GPT-4o）通常在生成更逼真对话方面优于其他模型，而较小的开源模型（如Llama、Mistral）在更高可定制性下展现出有前景的性能。我们证明通过采用监督微调技术可以显著提升较小模型的性能。然而，在所有模型中，保持连贯自然的长篇人类风格对话仍是一个共同挑战。
英文摘要：
Collecting human-chatbot dialogues typically demands substantial manual effort and is time-consuming, which limits and poses challenges for research on conversational AI. In this work, we propose DialogueForge - a framework for generating AI-simulated conversations in human-chatbot style. To initialize each generated conversation, DialogueForge uses seed prompts extracted from real human-chatbot interactions. We test a variety of LLMs to simulate the human chatbot user, ranging from state-of-the-art proprietary models to small-scale open-source LLMs, and generate multi-turn dialogues tailored to specific tasks. In addition, we explore fine-tuning techniques to enhance the ability of smaller models to produce indistinguishable human-like dialogues. We evaluate the quality of the simulated conversations and compare different models using the UniEval and GTEval evaluation protocols. Our experiments show that large proprietary models (e.g., GPT-4o) generally outperform others in generating more realistic dialogues, while smaller open-source models (e.g., Llama, Mistral) offer promising performance with greater customization. We demonstrate that the performance of smaller models can be significantly improved by employing supervised fine-tuning techniques. Nevertheless, maintaining coherent and natural long-form human-like dialogues remains a common challenge across all models.
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。
