Metraipolis › archive › dc_c90adee5fa77

Feedback-Assisted Trust Propagation over Document Relation Graphs for Retrieval-Augmented Generation — arXiv:2609.00543

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.00543
License (as archived): CC0-1.0
Archived: 2026-10-17T06:31:56.676Z
SHA-256 of the archived text: 24a4c70ce7ee593aeaaa06b50b72fa588828587ad0a4d91ecb53440fc26b21d5
Stable URL of this page: https://metraipolis.com/documento/dc_c90adee5fa77

How to cite

Feedback-Assisted Trust Propagation over Document Relation Graphs for Retrieval-Augmented Generation — arXiv:2609.00543 — arXiv (en), https://arxiv.org/abs/2609.00543 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c90adee5fa77 (Metraipolis archive dc_c90adee5fa77, sha256 24a4c70ce7ee593aeaaa06b50b72fa588828587ad0a4d91ecb53440fc26b21d5)

BibTeX

@misc{dcc90adee5fa77,
  title = {Feedback-Assisted Trust Propagation over Document Relation Graphs for Retrieval-Augmented Generation — arXiv:2609.00543},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00543},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c90adee5fa77; sha256 24a4c70ce7ee593aeaaa06b50b72fa588828587ad0a4d91ecb53440fc26b21d5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00543. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Retrieval-augmented generation (RAG) systems rely on external corpora that may contain outdated, contradictory, noisy, or unreliable documents, introducing reliability risks.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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.00543 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T06:15:12.615Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).