mlsanityData to 14 Oct 2026

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

arXiv 2504.18225 ↗First posted 25 Apr 2025cs.CLcited by 3

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

also in 1 more
Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 20 of its 38 references that are in the map. First posted on arXiv 25 Apr 2025.

Builds on

20 of 38 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning25 Mar

Other references · 19

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  3. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  4. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  5. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  6. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  7. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 788
  8. 20242 OLMo 2 Furiouscited by 340
  9. 2025Inference-Time Scaling for Generalist Reward Modelingcited by 239
  10. 2024A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthinesscited by 127
  11. 2023Effective Large Language Model Adaptation for Improved Grounding and Citation Generationcited by 45
  12. 2025Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Usecited by 45
7 more
  1. 2024Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Modelscited by 35
  2. 2024Scaling Laws for Fact Memorization of Large Language Modelscited by 33
  3. 2025InSTA: Towards Internet-Scale Training For Agentscited by 32
  4. 2024Improving Attributed Text Generation of Large Language Models via Preference Learningcited by 23
  5. 2024Large Language Models for Power Scheduling: A User-Centric Approachcited by 8
  6. 2024Citekit: A Modular Toolkit for Large Language Model Citation Generationcited by 5
  7. 2024On the Capacity of Citation Generation by Large Language Modelscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Models for minimalist RAG: B1ade 335M Embedding and 1B Parameter Small Language Modelscited by 1
  2. 2026OCC-RAG: Optimal Cognitive Core for Faithful Question Answeringcited by 0
  3. 2026Project Greenhouse: Progress Toward Fully Open and Sovereign Agentic Searchcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025LLMQuoter: Enhancing RAG Capabilities Through Efficient Quote Extraction From Large Contexts
  2. 2025Synergizing RAG and Reasoning: A Systematic Review
  3. 2024Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models
  4. 2025Lighting the Way for BRIGHT: Reproducible Baselines with Anserini, Pyserini, and RankLLM
  5. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs
  6. 2025Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals
  7. 2025RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning
  8. 2025Towards Global Retrieval Augmented Generation: A Benchmark for Corpus-Level Reasoning