analiza aiqbench
This benchmark reveals that while modern LLMs excel at semantic extraction from clean text, their utility degrades significantly under realistic OCR noise, where input quality becomes the dominant constraint over model size. The study identifies critical failure modes like numeric corruption and key-value misalignment, suggesting that future deployment strategies must jointly optimize OCR fidelity and structural reasoning rather than relying solely on larger models.
From Pixels to Pairs: A Comprehensive Benchmark of LLM-Based Key-Value Extraction in Noisy Document Settings
arXiv:2609.17538v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for structured information extraction from documents, yet their behavior under realistic OCR noise remains poorly understood. We present a systematic benchmark of open-source instruction-tuned LLMs for key-value pair (KVP) extraction under both clean-text and noisy OCR conditions. We evaluate representative decoder-only models (Gemma, Mistral, Qwen2.5, LLaMA 3, and DeepSeek) on the FUNSD, CORD, and SROIE benchmarks using both Gold-text annotations and OCR outputs from PaddleOCR, EasyOCR, and Tesseract. A unified evaluation protocol isolates the effects of input quality, model design, and prompting under consistent conditions. The results show that modern LLMs act as strong semantic extractors when high-quality text is available, in some cases approaching supervised layout-aware systems. Under OCR noise, however, performance degrades substantially and performance gaps between models narrow as input corruption increases. Across all datasets, extraction performance is governed by two factors: semantic reasoning over text and preservation of textual fidelity under OCR noise. While larger models improve results on clean text, these gains diminish under noisy inputs, where OCR quality becomes the dominant factor. We also identify recurring failure modes, including key-value misalignment, hallucination, and numeric corruption. Our findings highlight the gap between clean-text evaluation and real-world deployment, emphasizing the need to jointly improve OCR quality, structural reasoning, and LLM-based semantic modeling.
Abstract:Large language models (LLMs) are increasingly used for structured information extraction from documents, yet their behavior under realistic OCR noise remains poorly understood. We present a systematic benchmark of open-source instruction-tuned LLMs for key-value pair (KVP) extraction under both clean-text and noisy OCR conditions. We evaluate representative decoder-only models (Gemma, Mistral, Qwen2.5, LLaMA 3, and DeepSeek) on the FUNSD, CORD, and SROIE benchmarks using both Gold-text annotations and OCR outputs from PaddleOCR, EasyOCR, and Tesseract. A unified evaluation protocol isolates the effects of input quality, model design, and prompting under consistent conditions. The results show that modern LLMs act as strong semantic extractors when high-quality text is available, in some cases approaching supervised layout-aware systems. Under OCR noise, however, performance degrades substantially and performance gaps between models narrow as input corruption increases. Across all datasets, extraction performance is governed by two factors: semantic reasoning over text and preservation of textual fidelity under OCR noise. While larger models improve results on clean text, these gains diminish under noisy inputs, where OCR quality becomes the dominant factor. We also identify recurring failure modes, including key-value misalignment, hallucination, and numeric corruption. Our findings highlight the gap between clean-text evaluation and real-world deployment, emphasizing the need to jointly improve OCR quality, structural reasoning, and LLM-based semantic modeling.
Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2609.17538 [cs.CL]
(or arXiv:2609.17538v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.17538 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 312 cuvinte
Subiecte conexe
Frontier Risk Report (February to March 2026)
METR · 19 mai 2026
Informe de riesgos de la IA de frontera (febrero–marzo de 2026)
METR · 19 mai 2026
Frontier AI Risk Report (February–March 2026)
METR · 19 mai 2026
Reducing medical claims review time with AI on AWS: The EXL Medical IDP solution
AWS · 21 sept. 2026