Unverified50% confidenceFactExact time

The paper attributes extraction performance to two dominant factors: semantic reasoning capability over text and the preservation of text fidelity under OCR noise.

1

Sources

50%

Confidence

Long-term

Relevance

9/17/2026

First Seen

Sources

LLM Document Information Extraction Under OCR Noise: A Comprehensive Benchmark

Related Entities

From Pixels to Pairsconcept

Related Claims

UnverifiedThe experiments demonstrate that textual coherence can serve as an effective proxy indicator for detecting misleading content.70% similar UnverifiedThe authors cancel out the confounding effects of fluency and text quality by reading the same sentence with two different models.68% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/928482

API

curl https://kongchang.com/api/v1/knowledge/claims/928482

MCP

get_claim(id=928482)