mlsanityData to 14 Oct 2026

ProvenAI: Provenance-Native Traces of Evidence in Generated Answers

arXiv 2606.26449 ↗First posted 24 Jun 2026cs.CL cs.AI cs.CRcited by 1

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

Abstract (arXiv)

Retrieval-augmented systems routinely present citations alongside generated answers, yet a citation does not confirm that the corresponding source meaningfully shaped the output. This paper introduces ProvenAI, a framework that decomposes transparency in multi-hop question answering into three independently measurable layers: answer correctness, citation fidelity against benchmark supporting evidence, and per-document influence under leave-one-resource-out intervention. Targeting the HotpotQA distractor benchmark through a seven-stage pipeline covering data normalisation, retrieval indexing, citation-aware answer generation, attribution auditing, ablation-based influence estimation, batch evaluation, and interactive inspection, ProvenAI evaluates 7,405 validation examples drawn from a canonical corpus of 509,300 passages. The system achieves 53.53% answer accuracy alongside a mean citation-fidelity score of 71.55%, and a worked example surfaces what we call the citation-influence gap: a clean citation audit co-occurring with a profile in which one cited source registers only weak influence while seven uncited sources demonstrably shift the output. We formalise the relationship between the implemented surface proxy and a token-level KL-divergence target through a stated faithfulness condition, ground the framework in causal-mediation analysis and database-provenance theory, and discuss how the three measurement layers compose with cryptographic provenance architectures emerging in autonomous scientific discovery. ProvenAI establishes that meaningful transparency in retrieval-grounded QA requires traceable links across retrieved, cited, and behaviourally influential evidence as three distinct, independently measured layers.

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 26 of its 36 references that are in the map. First posted on arXiv 24 Jun 2026.

Builds on

26 of 36 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation19 Jun
  2. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct
  3. 2023Benchmarking Large Language Models in Retrieval-Augmented Generation4 Sep

Other references · 23

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2024Qwen2.5 Technical Reportcited by 4,942
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  7. 2017Billion-scale similarity search with GPUscited by 2,497
  8. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  9. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  10. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  11. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  12. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
11 more
  1. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  2. 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 418
  3. 2023Evaluating Verifiability in Generative Search Enginescited by 303
  4. 2024MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queriescited by 257
  5. 2021Measuring Attribution in Natural Language Generation Modelscited by 256
  6. 2024ContextCite: Attributing Model Generation to Contextcited by 98
  7. 2025SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Modelscited by 20
  8. 2025A Call to Action for a Secure-by-Design Generative AI Paradigmcited by 3
  9. 2025Cloud Investigation Automation Framework (CIAF): An AI-Driven Approach to Cloud Forensicscited by 3
  10. 2026Automating Cloud Security and Forensics Through a Secure-by-Design Generative AI Frameworkcited by 1
  11. 2026Predictive Maps of Multi-Agent Reasoning: A Successor-Representation Spectrum for LLM Communication Topologiescited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Agentic Cloud Decoys: A Deception-Driven Framework for Autonomous Intrusion Investigationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025VeriCite: Towards Reliable Citations in Retrieval-Augmented Generation via Rigorous Verification
  2. 2026CiteGuard-RAG: A Validation-Centered AI System for Evidence-Grounded Question Answering
  3. 2026PAGE-RAG: Provenance-Aware Graph Evidence Promotion for Fixed-Budget Multi-hop Retrieval-Augmented Generation
  4. 2026How Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation
  5. 2026DataDignity: Training Data Attribution for Large Language Models
  6. 2026AtomCite: Verification and Correction of Supplied Page-Level Citations in Multi-Page Documents
  7. 2026CUE-R: Beyond the Final Answer in Retrieval-Augmented Generation
  8. 2026SURE-RAG: Sufficiency and Uncertainty-Aware Evidence Verification for Selective Retrieval-Augmented Generation