ReceiptBench provides a 10k-receipt benchmark with four hierarchical VIE subtasks and a GRPO-based training framework that achieves SOTA results on receipt reasoning and parsing over proprietary models.
Flight” → plane) or implicit logic (e.g., “Double Room
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
From Recognition to Reasoning: Benchmarking and Enhancing MLLMs on Real-World Receipt Document Understanding
ReceiptBench provides a 10k-receipt benchmark with four hierarchical VIE subtasks and a GRPO-based training framework that achieves SOTA results on receipt reasoning and parsing over proprietary models.