# Up to 36x Speedup: Mask-based Parallel Inference Paradigm for Key Information Extraction in MLLMs

arXiv: https://arxiv.org/abs/2601.19613 · HTML: https://mlsanity.com/paper/2601.19613/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 21 of its 27 references that are in the map.
- First posted on arXiv 27 Jan 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/)

## Builds on (most cited first, 21 of 21)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [DeepSeek-VL: Towards Real-World Vision-Language Understanding](https://mlsanity.com/paper/2403.05525/) (2024)
- [GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models](https://mlsanity.com/paper/2508.06471/) (2025)
- [FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents](https://mlsanity.com/paper/1905.13538/) (2019)
- [LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding](https://mlsanity.com/paper/2306.17107/) (2023)
- [ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction](https://mlsanity.com/paper/2103.10213/) (2021)
- [DeepSeek-OCR: Contexts Optical Compression](https://mlsanity.com/paper/2510.18234/) (2025)
- [TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document](https://mlsanity.com/paper/2403.04473/) (2024)
- [LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding](https://mlsanity.com/paper/2404.05225/) (2024)
- [A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding](https://mlsanity.com/paper/2407.01976/) (2024)
- [Visual Information Extraction in the Wild: Practical Dataset and End-to-end Solution](https://mlsanity.com/paper/2305.07498/) (2023)
- [Spatial Dual-Modality Graph Reasoning for Key Information Extraction](https://mlsanity.com/paper/2103.14470/) (2021)
- [PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity Recognition](https://mlsanity.com/paper/2402.04838/) (2024)

## Abstract (arXiv)

Key Information Extraction (KIE) from visually-rich documents (VrDs) is a critical task, for which recent Large Language Models (LLMs) and Multi-Modal Large Language Models (MLLMs) have demonstrated strong potential. However, their reliance on autoregressive inference, which generates outputs sequentially, creates a significant efficiency bottleneck, especially as KIE tasks often involve extracting multiple, semantically independent fields. To overcome this limitation, we introduce PIP: a Parallel Inference Paradigm for KIE. Our approach reformulates the problem by using "[mask]" tokens as placeholders for all target values, enabling their simultaneous generation in a single forward pass. To facilitate this paradigm, we develop a tailored mask pre-training strategy and construct large-scale supervised datasets. Experimental results show that our PIP-models achieve a 5-36x inference speedup with negligible performance degradation compared to traditional autoregressive base models. By substantially improving efficiency while maintaining high accuracy, PIP paves the way for scalable and practical real-world KIE solutions.