In conversational AI research, there's a noticeable trend towards developing models with a larger number of parameters, exemplified by models like ChatGPT. While these expansive models tend to generate increasingly better chat responses, they demand significant computational resources and memory. This study explores a pertinent question: Can a combination of smaller models collaboratively achieve comparable or enhanced performance relative to a singular large model? We introduce an approach termed "blending", a straightforward yet effective method of integrating multiple chat AIs. Our empirical evidence suggests that when specific smaller models are synergistically blended, they can potentially outperform or match the capabilities of much larger counterparts. For instance, integrating just three models of moderate size (6B/13B paramaeters) can rival or even surpass the performance metrics of a substantially larger model like ChatGPT (175B+ paramaters). This hypothesis is rigorously tested using A/B testing methodologies with a large user base on the Chai research platform over a span of thirty days. The findings underscore the potential of the "blending" strategy as a viable approach for enhancing chat AI efficacy without a corresponding surge in computational demands.

翻译：在对话式人工智能研究中，存在一个显著趋势：模型参数规模不断扩大，ChatGPT 等模型即为典型代表。尽管这类大规模模型往往能生成更优质的聊天响应，但其运行需要大量计算资源与内存。本研究探讨了一个关键问题：多个较小模型的协同组合能否达到或超越单个大模型的性能？我们提出一种名为“融合”（blending）的方法，这是一种整合多个聊天 AI 的简单而高效的策略。实验证据表明，当特定较小模型以协同方式融合时，其性能可能超越或媲美远大于自身的模型。例如，仅整合三个中等规模（60亿/130亿参数）的模型，即可与参数规模超1750亿的 ChatGPT 等大模型相匹敌甚至更优。该假设通过基于 Chai 研究平台的大规模用户群体（为期30天）的 A/B 测试方法进行了严格验证。研究结果凸显了“融合”策略的潜力：它能在不显著增加计算需求的前提下，有效提升聊天 AI 的性能。