mlsanityData to 14 Oct 2026

PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning

arXiv 2507.18857 ↗First posted 25 Jul 2025cs.CL cs.AI cs.LGcited by 1

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

also in 1 more
Abstract (arXiv)

Retrieval-augmented generation (RAG) often falls short when retrieved context includes confusing semi-relevant passages, or when answering questions require deep contextual understanding and reasoning. We propose an efficient fine-tuning framework, called PrismRAG, that (i) trains the model with distractor-aware QA pairs mixing gold evidence with subtle distractor passages, and (ii) instills reasoning-centric habits that make the LLM plan, rationalize, and synthesize without relying on extensive human engineered instructions. Evaluated across 12 open-book RAG QA benchmarks spanning diverse application domains and scenarios, PrismRAG improves average factuality by 5.4%, outperforming state-of-the-art solutions.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 26 of its 43 references that are in the map. First posted on arXiv 25 Jul 2025.

Builds on

26 of 43 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Chain-of-Retrieval Augmented Generation24 Jan
  2. 2024Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training31 May

Other references · 24

  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. 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,288
  4. 2021FinQA: A Dataset of Numerical Reasoning over Financial Datacited by 562
  5. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 408
  6. 2024Measuring short-form factuality in large language modelscited by 373
  7. 2021CUAD: An Expert-Annotated NLP Dataset for Legal Contract Reviewcited by 236
  8. 2024Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?cited by 232
  9. 2023Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?cited by 168
  10. 2023Take a Step Back: Evoking Reasoning via Abstraction in Large Language Modelscited by 159
  11. 2024RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systemscited by 117
  12. 2024Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worsecited by 109
12 more
  1. 2023The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuningcited by 108
  2. 2023ExpertQA: Expert-Curated Questions and Attributed Answerscited by 97
  3. 2023WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipediacited by 67
  4. 2022Recitation-Augmented Language Modelscited by 65
  5. 2023HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attributioncited by 56
  6. 2024FLAME: Factuality-Aware Alignment for Large Language Modelscited by 47
  7. 2023DelucionQA: Detecting Hallucinations in Domain-specific Question Answeringcited by 43
  8. 2019The TechQA Datasetcited by 30
  9. 2021Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Frameworkcited by 21
  10. 2024ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Promptingcited by 8
  11. 2025LLMQuoter: Enhancing RAG Capabilities Through Efficient Quote Extraction From Large Contextscited by 4
  12. 2025ConfRAG: Confidence-Guided Retrieval-Augmenting Generationcited by 4

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025TruthRL: Incentivizing Truthful LLMs via Reinforcement Learningcited by 27

Similar, not cited

Close in wording, no citation either way

  1. 2025Retrieval as a Decision: Training-Free Adaptive Gating for Efficient RAG
  2. 2026Beyond Factual Accuracy: Evaluating Global Reasoning Integrity in RAG Systems with LogicScore
  3. 2025LIR3AG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented Generation
  4. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs
  5. 2025Evaluation of retrieval-based QA on QUEST-LOFT
  6. 2026When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering
  7. 2025Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization
  8. 2025EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notes