即便是小型推理模型也应引用其来源：介绍Pleias-RAG模型家族

摘要

我们推出了一代新型小型推理模型，专为RAG（检索增强生成）、搜索及源摘要任务设计。Pleias-RAG-350m与Pleias-RAG-1B在模拟从Common Corpus检索多种多语言开放资源的大型合成数据集上进行了中期训练。这些模型原生支持引用与基于直接引文的论据支撑，并整合了与RAG工作流相关的多项功能，如查询路由、查询重构及源重排序。在标准化RAG基准测试（如HotPotQA、2wiki）中，Pleias-RAG-350m与Pleias-RAG-1B的表现超越了参数规模低于40亿的SLM（小型语言模型），并与包括Qwen-2.5-7B、Llama-3.1-8B及Gemma-3-4B在内的流行大型模型相媲美。它们是迄今为止唯一能在主要欧洲语言间保持稳定RAG性能，并确保陈述系统引用基础的SLM。得益于其小巧的体积、在受限基础设施上的易部署性，以及设计上更高的真实性，这些模型为生成式AI开辟了一系列新的应用场景。

English

We introduce a new generation of small reasoning models for RAG, search, and source summarization. Pleias-RAG-350m and Pleias-RAG-1B are mid-trained on a large synthetic dataset emulating the retrieval of a wide variety of multilingual open sources from the Common Corpus. They provide native support for citation and grounding with literal quotes and reintegrate multiple features associated with RAG workflows, such as query routing, query reformulation, and source reranking. Pleias-RAG-350m and Pleias-RAG-1B outperform SLMs below 4 billion parameters on standardized RAG benchmarks (HotPotQA, 2wiki) and are competitive with popular larger models, including Qwen-2.5-7B, Llama-3.1-8B, and Gemma-3-4B. They are the only SLMs to date maintaining consistent RAG performance across leading European languages and ensuring systematic reference grounding for statements. Due to their size and ease of deployment on constrained infrastructure and higher factuality by design, the models unlock a range of new use cases for generative AI.

即便是小型推理模型也应引用其来源：介绍Pleias-RAG模型家族

Even Small Reasoners Should Quote Their Sources: Introducing the Pleias-RAG Model Family

摘要

Summary

Support

Support