mlsanityData to 7 Oct 2026

Feedback-Assisted Trust Propagation over Document Relation Graphs for Retrieval-Augmented Generation

arXiv 2609.00543 ↗First posted 1 Sep 2026cs.AIcited by 0

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

also in 1 more
Abstract (arXiv)

Retrieval-augmented generation (RAG) systems rely on external corpora that may contain outdated, contradictory, noisy, or unreliable documents, introducing reliability risks. Prior work has leveraged document relations to improve the answer reliability of RAG. To propagate reliability signals beyond directly compared document pairs, we propose TrustPropRAG, which structures document relations as a graph and estimates document reliability through multi-hop propagation across the graph. TrustPropRAG anchors this propagation with a limited set of human feedback on document reliability, extending these costly-to-collect feedback-based reliability signals across the whole corpus. Specifically, based on the constructed document relation graph, TrustPropRAG estimates a trust score for each document by formulating and solving an optimization problem that jointly captures pairwise document relations and user feedback. These scores are then used to improve the selection of reliable documents and support trust-aware answer generation. Evaluation results show that TrustPropRAG improves both retrieval quality and exact match over baselines, and remains robust under sparse and noisy feedback.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 25 of its 39 references that are in the map. First posted on arXiv 1 Sep 2026.

Builds on

25 of 39 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Retrieval-Augmented Generation with Estimation of Source Reliability30 Oct
  2. 2024InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales19 Jun

Other references · 23

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  5. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  6. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  7. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  8. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  9. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  10. 2023Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflictscited by 333
  11. 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 310
  12. 2024Knowledge Conflicts for LLMs: A Surveycited by 274
11 more
  1. 2023Poisoning Retrieval Corpora by Injecting Adversarial Passagescited by 153
  2. 2024Certifiably Robust RAG against Retrieval Corruptioncited by 144
  3. 2022Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidencecited by 142
  4. 2024ContextCite: Attributing Model Generation to Contextcited by 93
  5. 2019Reasoning Over Semantic-Level Graph for Fact Checkingcited by 69
  6. 2025TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generationcited by 37
  7. 2025NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodescited by 25
  8. 2025User Feedback in Human-LLM Dialogues: A Lens to Understand Users But Noisy as a Learning Signalcited by 19
  9. 2024Open Domain Question Answering with Conflicting Contextscited by 18
  10. 2025ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Searchcited by 17
  11. 2024Pistis-RAG: Enhancing Retrieval-Augmented Generation with Human Feedbackcited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025ClaimTrust: Propagation Trust Scoring for RAG Systems
  2. 2025After Retrieval, Before Generation: Enhancing the Trustworthiness of Large Language Models in Retrieval-Augmented Generation
  3. 2024Trustworthiness in Retrieval-Augmented Generation Systems: A Survey
  4. 2026A Systems-Level Analysis of Sensitivity, Robustness, and Stability in Retrieval-Augmented Generation
  5. 2025Test-time Corpus Feedback: From Retrieval to RAG
  6. 2025TrustRAG: An Information Assistant with Retrieval Augmented Generation
  7. 2025InfoGain-RAG: Boosting Retrieval-Augmented Generation via Document Information Gain-based Reranking and Filtering
  8. 2025Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey