mlsanityData to 14 Oct 2026

TrustRAG: An Information Assistant with Retrieval Augmented Generation

arXiv 2502.13719 ↗First posted 19 Feb 2025cs.IR cs.AIcited by 1

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

AcRAG has emerged as a crucial technique for enhancing large models with real-time and domain-specific knowledge. While numerous improvements and open-source tools have been proposed to refine the acRAG framework for accuracy, relatively little attention has been given to improving the trustworthiness of generated results. To address this gap, we introduce TrustRAG, a novel framework that enhances acRAG from three perspectives: indexing, retrieval, and generation. Specifically, in the indexing stage, we propose a semantic-enhanced chunking strategy that incorporates hierarchical indexing to supplement each chunk with contextual information, ensuring semantic completeness. In the retrieval stage, we introduce a utility-based filtering mechanism to identify high-quality information, supporting answer generation while reducing input length. In the generation stage, we propose fine-grained citation enhancement, which detects opinion-bearing sentences in responses and infers citation relationships at the sentence-level, thereby improving citation accuracy. We open-source the TrustRAG framework and provide a demonstration studio designed for excerpt-based question answering tasks footnotehttps://huggingface.co/spaces/golaxy/TrustRAG. Based on these, we aim to help researchers: 1) systematically enhancing the trustworthiness of acRAG systems and (2) developing their own acRAG systems with more reliable outputs.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 18 of its 23 references that are in the map. First posted on arXiv 19 Feb 2025.

Builds on

18 of 23 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Trustworthiness in Retrieval-Augmented Generation Systems: A Survey16 Sep
  2. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 16

  1. 2023A Survey of Large Language Modelscited by 2,576
  2. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  3. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 532
  4. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 354
  5. 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 315
  6. 2024A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Modelscited by 269
  7. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Researchcited by 166
  8. 2024RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systemscited by 117
  9. 2024LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QAcited by 81
  10. 2024StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurizationcited by 71
  11. 2025Chain-of-Retrieval Augmented Generationcited by 49
  12. 2025DeepRAG: Thinking to Retrieve Step by Step for Large Language Modelscited by 38
4 more
  1. 2023Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applicationscited by 28
  2. 2025SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Modelscited by 20
  3. 2024ThinkNote: Enhancing Knowledge Integration and Utilization of Large Language Models via Constructivist Cognition Modelingcited by 8
  4. 2024RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generationcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Enhancing Scientific Literature Chatbots with Retrieval-Augmented Generation: A Performance Evaluation of Vector and Graph-Based Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generation
  2. 2026KohakuRAG: A simple RAG framework with hierarchical document indexing
  3. 2025mmRAG: A Modular Benchmark for Retrieval-Augmented Generation over Text, Tables, and Knowledge Graphs
  4. 2025Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey
  5. 2024Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation
  6. 2025VeriCite: Towards Reliable Citations in Retrieval-Augmented Generation via Rigorous Verification
  7. 2025HiPerRAG: High-Performance Retrieval Augmented Generation for Scientific Insights
  8. 2025CiteFix: Enhancing RAG Accuracy Through Post-Processing Citation Correction