mlsanityData to 14 Oct 2026

From Binary Groundedness to Support Relations: Towards a Reader-Centred Taxonomy for Comprehension of AI Output

arXiv 2604.08082 ↗First posted 9 Apr 2026cs.HCcited by 0

On the map: Retrieval-augmented generation → Hallucination detection in RAG

Abstract (arXiv)

Generative AI tools often answer questions using source documents, e.g., through retrieval augmented generation. Current groundedness and hallucination evaluations largely frame the relationship between an answer and its sources as binary (the answer is either supported or unsupported). However, this obscures both the syntactic moves (e.g., direct quotation vs. paraphrase) and the interpretive moves (e.g., induction vs. deduction) performed when models reformulate evidence into an answer. This limits both benchmarking and user-facing provenance interfaces. We propose the development of a reader-centred taxonomy of grounding as a set of support relations between generated statements and source documents. We explain how this might be synthesised from prior research in linguistics and philosophy of language, and evaluated through a benchmark and human annotation protocol. Such a framework would enable interfaces that communicate not just whether a claim is grounded, but how.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Hallucination detection in RAG, one of 15 directions in Retrieval-augmented generation. Builds on 22 of its 44 references that are in the map. First posted on arXiv 9 Apr 2026.

Builds on

22 of 44 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models31 Dec

Other references · 21

  1. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  2. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  3. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  4. 2021Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metricscited by 287
  5. 2021A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generationcited by 138
  6. 2023The Metacognitive Demands and Opportunities of Generative AIcited by 87
  7. 2023Beyond the Chat: Executable and Verifiable Text-Editing with LLMscited by 35
  8. 2024Evaluating the Evaluator: Measuring LLMs' Adherence to Task Evaluation Instructionscited by 34
  9. 2023FactCHD: Benchmarking Fact-Conflicting Hallucination Detectioncited by 29
  10. 2024Improving Steering and Verification in AI-Assisted Data Analysis with Interactive Task Decompositioncited by 29
  11. 2023DataTales: Investigating the use of Large Language Models for Authoring Data-Driven Articlescited by 24
  12. 2025Towards Effective Extraction and Evaluation of Factual Claimscited by 19
9 more
  1. 2024DiaHalu: A Dialogue-level Hallucination Evaluation Benchmark for Large Language Modelscited by 15
  2. 2023Exploring Perspectives on the Impact of Artificial Intelligence on the Creativity of Knowledge Work: Beyond Mechanised Plagiarism and Stochastic Parrotscited by 11
  3. 2024Large Language Models Cannot Explain Themselvescited by 11
  4. 2024AI Should Challenge, Not Obeycited by 11
  5. 2024GenAudit: Fixing Factual Errors in Language Model Outputs with Evidencecited by 10
  6. 2023Qlarify: Recursively Expandable Abstracts for Directed Information Retrieval over Scientific Paperscited by 8
  7. 2024When Copilot Becomes Autopilot: Generative AI's Critical Risk to Knowledge Work and a Critical Solutioncited by 3
  8. 2025Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answerscited by 3
  9. 2025FACTS&EVIDENCE: An Interactive Tool for Transparent Fine-Grained Factual Verification of Machine-Generated Textcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026The Token Tax of Epistemic Accuracy: Comparing RAG and Long-Context Architectures for Document-Grounded Generative AI Applications
  2. 2024"Understanding AI": Semantic Grounding in Large Language Models
  3. 2024Measuring the Groundedness of Legal Question-Answering Systems
  4. 2024Groundedness in Retrieval-augmented Long-form Generation: An Empirical Study
  5. 2023Grounding Gaps in Language Model Generations
  6. 2026Detecting and Repairing Hallucinations in Retrieval-Augmented Generation
  7. 2026The Grounding Gap: How LLMs Anchor the Meaning of Abstract Concepts Differently from Humans
  8. 2026Beyond Hooking Onto the World: Referential Profiles and the Numerical Structure of LLM Grounding