Papers by Atin Ghosh
OCR or Not? Rethinking Document Information Extraction in the MLLMs Era with Real-World Large-Scale Datasets (2026.eacl-industry)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) are used for document information extraction, but their impact on document information processing remains unclear. |
| Approach: | They propose an automated hierarchical error analysis framework that leverages large language models to diagnose errors systematically. |
| Outcome: | The proposed framework can achieve comparable performance to OCR-enhanced approaches. |
Optimization before Evaluation: Evaluation with Unoptimized Prompts Can be Misleading (2025.acl-industry)
Copied to clipboard
| Challenge: | Current Large Language Model (LLM) evaluation frameworks use the same static prompt template across all models under evaluation. |
| Approach: | They investigate the effect of PO on LLM evaluations by using public academic and internal benchmarks to optimize the prompt for each model. |
| Outcome: | The proposed frameworks use the same static prompt template across all models under evaluation, but have some drawbacks. |