Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Alessio, Giovannini, Simone, Gemelli, Andrea, Coppini, Fabio, Marinai, Simone
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.10129
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911152523444224
author Chen, Alessio
Giovannini, Simone
Gemelli, Andrea
Coppini, Fabio
Marinai, Simone
author_facet Chen, Alessio
Giovannini, Simone
Gemelli, Andrea
Coppini, Fabio
Marinai, Simone
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_10129
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Reliable and Interpretable Document Question Answering via VLMs
Chen, Alessio
Giovannini, Simone
Gemelli, Andrea
Coppini, Fabio
Marinai, Simone
Computation and Language
Information Retrieval
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.
title Towards Reliable and Interpretable Document Question Answering via VLMs
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/2509.10129