mlsanityData to 14 Oct 2026

Trust but Verify: Introducing DAVinCI -- A Framework for Dual Attribution and Verification in Claim Inference for Language Models

arXiv 2604.21193 ↗First posted 23 Apr 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) have demonstrated remarkable fluency and versatility across a wide range of NLP tasks, yet they remain prone to factual inaccuracies and hallucinations. This limitation poses significant risks in high-stakes domains such as healthcare, law, and scientific communication, where trust and verifiability are paramount. In this paper, we introduce DAVinCI - a Dual Attribution and Verification framework designed to enhance the factual reliability and interpretability of LLM outputs. DAVinCI operates in two stages: (i) it attributes generated claims to internal model components and external sources; (ii) it verifies each claim using entailment-based reasoning and confidence calibration. We evaluate DAVinCI across multiple datasets, including FEVER and CLIMATE-FEVER, and compare its performance against standard verification-only baselines. Our results show that DAVinCI significantly improves classification accuracy, attribution precision, recall, and F1-score by 5-20%. Through an extensive ablation study, we isolate the contributions of evidence span selection, recalibration thresholds, and retrieval quality. We also release a modular DAVinCI implementation that can be integrated into existing LLM pipelines. By bridging attribution and verification, DAVinCI offers a scalable path to auditable, trustworthy AI systems. This work contributes to the growing effort to make LLMs not only powerful but also accountable.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 17 references that are in the map. First posted on arXiv 23 Apr 2026.

Builds on

13 of 17 references.

References · 13

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2017On Calibration of Modern Neural Networkscited by 4,960
  3. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  4. 2023A Survey of Hallucination in Large Foundation Modelscited by 368
  5. 2023Evaluating Verifiability in Generative Search Enginescited by 303
  6. 2020CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claimscited by 196
  7. 2019MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claimscited by 169
  8. 2023The Troubling Emergence of Hallucination in Large Language Models -- An Extensive Definition, Quantification, and Prescriptive Remediationscited by 131
  9. 2022Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completioncited by 102
  10. 2018Automated Fact Checking: Task formulations, methods and future directionscited by 96
  11. 2018ClaimRank: Detecting Check-Worthy Claims in Arabic and Englishcited by 27
  12. 2024FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluationcited by 25
1 more
  1. 2024Claim Verification in the Age of Large Language Models: A Surveycited by 24

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data
  2. 2026Towards Comprehensive Stage-wise Benchmarking of Large Language Models in Fact-Checking
  3. 2026Claim-Level Confidence Calibration for Reliable Decision Making with Large Language Models
  4. 2026InFi-Check: Interpretable and Fine-Grained Fact-Checking of LLMs
  5. 2026Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval
  6. 2023LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond
  7. 2024AFaCTA: Assisting the Annotation of Factual Claim Detection with Reliable LLM Annotators
  8. 2026Fact-Checking with Large Language Models via Probabilistic Certainty and Consistency