# Towards Reliable and Interpretable Document Question Answering via VLMs

Source: [Towards Reliable and Interpretable Document Question Answering via VLMs](<https://www.sota2.com/research/paper/68fa7b511e209131cea87c2c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:37:33.682Z

Authors: Alessio Chen, Simone Giovannini, Andrea Gemelli, Fabio Coppini, Simone Marinai

Published: 2025-09-12T10:44:24.000Z

## Abstract

Vision-Language Models (VLMs) have shown strong capabilities in document understanding, particularly in identifying and extracting textual information from complex documents. Despite this, accurately localizing answers within documents remains a major challenge, limiting both interpretability and real-world applicability. To address this, we introduce DocExplainerV0, a plug-and-play bounding-box prediction module that decouples answer generation from spatial localization. This design makes it applicable to existing VLMs, including proprietary systems where fine-tuning is not feasible. Through systematic evaluation, we provide quantitative insights into the gap between textual accuracy and spatial grounding, showing that correct answers often lack reliable localization. Our standardized framework highlights these shortcomings and establishes a benchmark for future research toward more interpretable and robust document information extraction VLMs.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2509.10129>)

[PDF](<https://arxiv.org/pdf/2509.10129.pdf>)