DocVLM-Fingerprint: Document VLM Faithfulness Under Visual Perturbations

Abstract DocVLM-Fingerprint studies a narrow failure mode in document visual question answering (VQA): a vision-language model (VLM) can return a plausible short answer while its accompanying claim is unsupported by the annotated evidence. This work implements a reproducible evaluation pipeline for generated chart, optical character recognition (OCR) document, and scientific figure tasks. The pipeline includes four visual perturbations, open VLM clients, answer scoring, claim-support labels, plots, and failure records. The main run covers 120 generated examples, 480 perturbed variants, and three open models. Small clean subsets of ChartQA and DocumentVQA, together with a Qwen-only CharXiv perturbation supplement using real charts, provide external checks. The evidence supports a controlled diagnostic study of failure patterns, not a general ranking of VLMs.

Authors

Publication Details

Journal
Research Square
Published
2026-11-17
DOI
https://doi.org/10.21203/rs.3.rs-11757192/v1
Primary Topic
Multimodal Machine Learning Applications
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

DocVLM-Fingerprint: Document VLM Faithfulness Under Visual Perturbations

Samarth Kukreja
Research Square
Multimodal Machine Learning Applications
preprint

DocVLM-Fingerprint: Document VLM Faithfulness Under Visual Perturbations

Samarth Kukreja
preprint en

Abstract

Abstract DocVLM-Fingerprint studies a narrow failure mode in document visual question answering (VQA): a vision-language model (VLM) can return a plausible short answer while its accompanying claim is unsupported by the annotated evidence. This work implements a reproducible evaluation pipeline for generated chart, optical character recognition (OCR) document, and scientific figure tasks. The pipeline includes four visual perturbations, open VLM clients, answer scoring, claim-support labels, plots, and failure records. The main run covers 120 generated examples, 480 perturbed variants, and three open models. Small clean subsets of ChartQA and DocumentVQA, together with a Qwen-only CharXiv perturbation supplement using real charts, provide external checks. The evidence supports a controlled diagnostic study of failure patterns, not a general ranking of VLMs.

Research Square
Multimodal Machine Learning Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon