The unparalleled performance of closed-sourced ChatGPT has sparked efforts towards its democratization, with notable strides made by leveraging real user and ChatGPT conversations, as evidenced by Vicuna. However, due to challenges in gathering conversations involving human participation, current endeavors like Baize and UltraChat aim to automatically generate conversational data. They primarily rely on ChatGPT conducting roleplay to simulate human behaviors based on instructions rather than genuine learning from humans, resulting in limited scope, diminished diversity, and an absence of genuine multi-round conversational dynamics. To address the above issues, we target human questions extracted from genuine human-machine conversations as a learning goal and train a user simulator called `Socratic' to produce a high-quality human-centric synthetic conversation dataset. Subsequently, this dataset was used to train our assistant model, named `PlatoLM'. Experimentally, PlatoLM outpaces baseline models in both Vicuna-Bench and MT-Bench by pairwise comparison when considering equivalent training set sizes, and manual evaluation also shows that our model is highly competitive. Impressively, when fine-tuned with the latest LLaMA 2 model, PlatoLM achieves the SOTA performance among 7B models (including LLaMA-2-7B-chat and Vicuna-7B) in MT-Bench benchmark and in Alpaca-Eval benchmark, it ranks second among 7B models, even beating some larger scale models (including LLaMA-2-13B-chat and GPT-3.5). Further in-depth analysis demonstrates the scalability and transferability of our approach. The code is available at https://github.com/FreedomIntelligence/PlatoLM.

翻译：闭源ChatGPT的卓越性能推动了其民主化进程，通过利用真实用户与ChatGPT的对话数据（如Vicuna所示）已取得显著进展。然而，由于收集有人类参与的对话数据面临挑战，现有研究（如Baize和UltraChat）致力于自动生成对话数据。这些方法主要依赖ChatGPT通过角色扮演模拟人类行为，但基于指令而非真实人类学习，导致数据范围有限、多样性不足，且缺乏真实的多轮对话动态特征。为解决上述问题，我们以真实人机对话中的人类提问为目标学习点，训练了一个名为“Socratic”的用户模拟器，以生成高质量、以人为核心的合成对话数据集。随后利用该数据集训练我们的助理解释模型“柏拉图语言模型”。实验表明，在同等训练集规模下，柏拉图语言模型在Vicuna-Bench和MT-Bench基准测试中的成对比较中均优于基线模型，人工评估也显示其具备高度竞争力。值得关注的是，当基于最新LLaMA 2模型微调时，柏拉图语言模型在MT-Bench基准测试中达到7B参数模型（包括LLaMA-2-7B-chat和Vicuna-7B）的最优性能，并在Alpaca-Eval基准测试中位列7B模型第二，甚至超越部分更大规模模型（包括LLaMA-2-13B-chat和GPT-3.5）。进一步深度分析证明了我们方法的可扩展性与可迁移性。代码已开源至https://github.com/FreedomIntelligence/PlatoLM。