mlsanityData to 14 Oct 2026

EvidenT: Building Trustworthy Enterprise Assistants through Evidence Groundedness and Traceability

arXiv 2609.22537 ↗First posted 18 Sep 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Enterprise AI assistants must produce responses that are verifiable and traceable to source evidence. However, retrieval augmented generation (RAG) over heterogeneous enterprise data can suffer from citation drift, unsupported content, and weak source traceability. We present EvidenT (T = Trust + Transparency + Traceability), a lightweight pipeline that verifies extracted evidence against retrieved documents before answer generation, without model retraining. EvidenT combines structured passage extraction with deterministic lexical alignment to filter unsupported content, correct citation drift, and preserve source-span traceability. On approximately 500 real enterprise queries, EvidenT improves gold-source hit rate by an average of 29% over prompting baselines, produces no citations to nonretrieved urls, and achieves near-saturated answer-to-source lexical coverage.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 34 references that are in the map. First posted on arXiv 18 Sep 2026.

Builds on

25 of 34 references.

References · 25

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
  3. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  5. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,346
  6. 2024Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Surveycited by 656
  7. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  8. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 584
  9. 2021SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarizationcited by 407
  10. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documentscited by 257
  11. 2017Why We Need New Evaluation Metrics for NLGcited by 233
  12. 2021Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Featurescited by 74
13 more
  1. 2024A Survey on Large Language Models for Critical Societal Domains: Finance, Healthcare, and Lawcited by 74
  2. 2024Sufficient Context: A New Lens on Retrieval Augmented Generation Systemscited by 72
  3. 2024Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledgecited by 50
  4. 2024Understanding Finetuning for Factual Knowledge Extractioncited by 32
  5. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontierscited by 27
  6. 2025StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputscited by 25
  7. 2024Evidence-backed Fact Checking using RAG and Few-Shot In-Context Learning with LLMscited by 24
  8. 2025Benchmarking Deep Search over Heterogeneous Enterprise Datacited by 23
  9. 2024Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generationcited by 21
  10. 2025CiteEval: Principle-Driven Citation Evaluation for Source Attributioncited by 19
  11. 2025A Systematic Literature Review of Retrieval-Augmented Generation: Techniques, Metrics, and Challengescited by 17
  12. 2025VeriCite: Towards Reliable Citations in Retrieval-Augmented Generation via Rigorous Verificationcited by 8
  13. 2024Optimizing and Evaluating Enterprise Retrieval-Augmented Generation (RAG): A Content Design Perspectivecited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Orchestrating Specialized Agents for Trustworthy Enterprise RAG
  2. 2026ERA: Evidence-based Reliability Alignment for Honest Retrieval-Augmented Generation
  3. 2026ProvenAI: Provenance-Native Traces of Evidence in Generated Answers
  4. 2026SURE-RAG: Sufficiency and Uncertainty-Aware Evidence Verification for Selective Retrieval-Augmented Generation
  5. 2026AgenticRAG: Agentic Retrieval for Enterprise Knowledge Bases
  6. 2026CiteGuard-RAG: A Validation-Centered AI System for Evidence-Grounded Question Answering
  7. 2026RCL: A Retrieval-Confidence Layer for Detecting Insufficient Context in Enterprise Retrieval-Augmented Code Generation
  8. 2025Rethinking All Evidence: Enhancing Trustworthy Retrieval-Augmented Generation via Conflict-Driven Summarization