即便是小型推理者也應引用其來源：介紹Pleias-RAG模型家族

摘要

我們推出新一代小型推理模型，專為RAG（檢索增強生成）、搜索及來源摘要而設計。Pleias-RAG-350m和Pleias-RAG-1B在一個大型合成數據集上進行了中期訓練，該數據集模擬了從Common Corpus中檢索多種多語言開放來源的過程。這些模型原生支持引用和基於字面引用的基礎驗證，並重新整合了與RAG工作流相關的多項功能，如查詢路由、查詢重構和來源重新排序。在標準化的RAG基準測試（如HotPotQA、2wiki）中，Pleias-RAG-350m和Pleias-RAG-1B的表現優於參數低於40億的小型語言模型（SLMs），並與包括Qwen-2.5-7B、Llama-3.1-8B和Gemma-3-4B在內的流行大型模型競爭。它們是迄今為止唯一能在主要歐洲語言中保持一致的RAG性能，並確保對陳述進行系統性參考基礎驗證的SLMs。由於其體積小巧、易於在受限基礎設施上部署，以及設計上更高的真實性，這些模型為生成式AI開闢了一系列新的應用場景。

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.

即便是小型推理者也應引用其來源：介紹Pleias-RAG模型家族

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

摘要

Summary

Support

Support