AutoVerifier: An Agentic Automated Verification Framework Using Large Language Models
Yuntao Du, Minh Dinh, Kaiyuan Zhang, Ninghui Li
TLDR
AutoVerifier is an LLM-based agentic framework that automates end-to-end verification of complex technical claims, identifying inconsistencies and conflicts of interest.
Key contributions
- LLM-based agentic framework automates end-to-end verification of complex technical claims.
- Decomposes assertions into structured claim triples, building knowledge graphs for reasoning.
- Performs multi-layered verification: intra-document, cross-source, and external corroboration.
- Identified overclaims, inconsistencies, and conflicts of interest in a quantum computing case.
Why it matters
This paper introduces a novel LLM-based framework that bridges the gap in verifying complex technical claims, moving beyond surface-level accuracy to deeper methodological validity. It empowers non-domain experts to reliably evaluate emerging technologies, transforming raw documents into traceable, evidence-backed intelligence assessments.
Original Abstract
Scientific and Technical Intelligence (S&TI) analysis requires verifying complex technical claims across rapidly growing literature, where existing approaches fail to bridge the verification gap between surface-level accuracy and deeper methodological validity. We present AutoVerifier, an LLM-based agentic framework that automates end-to-end verification of technical claims without requiring domain expertise. AutoVerifier decomposes every technical assertion into structured claim triples of the form (Subject, Predicate, Object), constructing knowledge graphs that enable structured reasoning across six progressively enriching layers: corpus construction and ingestion, entity and claim extraction, intra-document verification, cross-source verification, external signal corroboration, and final hypothesis matrix generation. We demonstrate AutoVerifier on a contested quantum computing claim, where the framework, operated by analysts with no quantum expertise, automatically identified overclaims and metric inconsistencies within the target paper, traced cross-source contradictions, uncovered undisclosed commercial conflicts of interest, and produced a final assessment. These results show that structured LLM verification can reliably evaluate the validity and maturity of emerging technologies, turning raw technical documents into traceable, evidence-backed intelligence assessments.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.