Search papers, labs, and topics across Lattice.
DAVinCI, a Dual Attribution and Verification framework, is introduced to improve the factual reliability of LLM outputs by attributing claims to internal model components and external sources, then verifying them using entailment-based reasoning and confidence calibration. Experiments on FEVER and CLIMATE-FEVER datasets show that DAVinCI improves classification accuracy, attribution precision, recall, and F1-score by 5-20% compared to verification-only baselines. The modular DAVinCI implementation offers a scalable approach to building auditable and trustworthy AI systems.
LLMs can be made 20% more reliable by attributing claims to their origins and verifying them, a strategy that beats verification alone.
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.
