{"type":"ScholarlyArticle","title":"IKnowFlow: Trustworthy RAG for Sensitive Domains","authors":[{"name":"Yash Saxena","slug":"yash-saxena","given":"Yash","family":"Saxena","affiliation":""}],"abstract":"RAG systems ground LLM responses in external evidence, yet their trustworthiness remains underspecified. Retrieval, re-ranking, and generation are optimized independently with no unified account of whether the system is interpretable, grounded, and traceable. My thesis operationalizes trustworthy RAG through three current sub-goals, each at the stage where it is most vulnerable. For traceability, REASONS benchmarks LLMs on 20K papers, showing attribution failures are systematic even under retrieval augmentation. For interpretability, IMRNNs decomposes dense embeddings via learned adapters, exposing human-readable query-document matching at retrieval. For grounding, METEORA replaces opaque re-ranking with rationale-driven selection, ensuring generation operates over explicitly justified context. I unify these under Interpretable Knowledge Flow (IKnowFlow), where trustworthiness is preserved across stage boundaries rather than checked at output. IKnowFlow will next address two longstanding blind spots: negation-awareness in retrieval, where surface similarity masks semantic inversion, and provenance-aware verification through structured source graphs.","doi":"10.24963/ijcai.2026/947","url":"https://ijcai.org/proceedings/2026/947","pdf":"https://ijcai.org/proceedings/2026/0947.pdf","markdown":"https://ijcai.org/proceedings/2026/947.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/947","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Doctoral Consortium","track":"Doctoral Consortium","number":947,"pages":{"first":8337,"last":8338},"keywords":["Machine Learning: Neuro-symbolic methods/Abductive Learning","Natural Language Processing: Information retrieval and text mining","AI Ethics, Trust, Fairnes: Trustworthy AI","Natural Language Processing: Language grounding"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}