mlsanityData to 7 Oct 2026

FVA-RAG: Falsification-Verification Alignment for Mitigating Sycophantic Hallucinations

arXiv 2512.07015 ↗First posted 7 Dec 2025cs.CL cs.AI cs.IRcited by 1

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

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) reduces hallucinations by grounding answers in retrieved evidence, yet standard retrievers often exhibit retrieval sycophancy: they preferentially surface evidence that supports a user's premise, even when the premise is false. We propose FVA-RAG (Falsification-Verification Alignment RAG), a pipeline that inverts the standard RAG workflow by treating the initial response as a draft hypothesis and explicitly retrieving anti-context to stress-test it. We evaluate on the full TruthfulQA-Generation benchmark (N=817) under a fully frozen protocol with 0 live web calls and identical retrieval budgets across methods. Using gpt-4o for generation and deterministic judging, FVA-RAG achieves 79.80-80.05% accuracy across two independently built frozen corpora , significantly outperforming prompted variants of Self-RAG (71.11-72.22%) and CRAG (71.36-73.93%) with p < 10^-6 according to McNemar's test. FVA-RAG triggers falsification on 24.5-29.3% of queries, demonstrating that targeted counter-evidence retrieval is decisive for mitigating premise-confirming hallucinations.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Hallucination detection in RAG, one of 15 directions in Retrieval-augmented generation. Builds on 5 of its 11 references that are in the map. First posted on arXiv 7 Dec 2025.

Builds on

5 of 11 references.

References · 5

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  3. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  4. 2025Causal-Counterfactual RAG: The Integration of Causal-Counterfactual Reasoning into RAGcited by 2
  5. 2025Enhancing Retrieval Augmentation via Adversarial Collaborationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026ArbGraph: Conflict-Aware Evidence Arbitration for Reliable Long-Form Retrieval-Augmented Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models
  2. 2026Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented Generation
  3. 2026Retromorphic Testing with Hierarchical Verification for Hallucination Detection in RAG
  4. 2025Osiris: A Lightweight Open-Source Hallucination Detection System
  5. 2025MetaRAG: Metamorphic Testing for Hallucination Detection in RAG Systems
  6. 2024100% Elimination of Hallucinations on RAGTruth for GPT-4 and GPT-3.5 Turbo
  7. 2025The Semantic Illusion: Certified Limits of Embedding-Based Hallucination Detection in RAG Systems
  8. 2026RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration