CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence
CiteVQA introduces a new benchmark that forces models to provide precise, element-level citations for every answer. The evaluation uses Strict Attributed Accuracy (SAA) to check if both the answer and its cited evidence are correct. Audits reveal 'Attribution Hallucination,' where models correctly answer but cite the wrong parts of a document, highlighting a major gap in multimodal reliability.