Search papers, labs, and topics across Lattice.
RaV-IDP is introduced as a novel document processing pipeline that uses reconstruction and comparison to validate the fidelity of extracted entities (tables, images, text) against the original document. After extraction, a reconstructor renders the extracted representation back into a form comparable to the original document region, and a comparator scores fidelity between the reconstruction and the unmodified source crop. This fidelity score is then used to trigger a GPT-4.1 vision fallback when fidelity falls below a threshold, improving the accuracy and reliability of document processing pipelines.
By reconstructing extractions and comparing them to the original document, RaV-IDP offers a grounded, label-free quality signal that dramatically improves the fidelity of intelligent document processing pipelines.
Intelligent document processing pipelines extract structured entities (tables, images, and text) from documents for use in downstream systems such as knowledge bases, retrieval-augmented generation, and analytics. A persistent limitation of existing pipelines is that extraction output is produced without any intrinsic mechanism to verify whether it faithfully represents the source. Model-internal confidence scores measure inference certainty, not correspondence to the document, and extraction errors pass silently into downstream consumers. We present Reconstruction as Validation (RaV-IDP), a document processing pipeline that introduces reconstruction as a first-class architectural component. After each entity is extracted, a dedicated reconstructor renders the extracted representation back into a form comparable to the original document region, and a comparator scores fidelity between the reconstruction and the unmodified source crop. This fidelity score is a grounded, label-free quality signal. When fidelity falls below a per-entity-type threshold, a structured GPT-4.1 vision fallback is triggered and the validation loop repeats. We enforce a bootstrap constraint: the comparator always anchors against the original document region, never against the extraction, preventing the validation from becoming circular. We further propose a per-stage evaluation framework pairing each pipeline component with an appropriate benchmark. The code pipeline is publicly available at https://github.com/pritesh-2711/RaV-IDP for experimentation and use.
