Across three invoice datasets, multimodal LLMs extract fields more accurately from raw images than from markdown converted by a parsing tool, with Gemini 2.5 Pro leading.
Field extraction from forms with unlabeled data,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Multi-Modal Vision vs. Text-Based Parsing: Benchmarking LLM Strategies for Invoice Processing
Across three invoice datasets, multimodal LLMs extract fields more accurately from raw images than from markdown converted by a parsing tool, with Gemini 2.5 Pro leading.