Improving MLLM Historical Record Extraction with Test-Time Image

W e present a novel ensemble framework that stabilizes LLM-based text extraction from noisy historical documents. W e transcribe multiple augmented variants of each image with Gemini 2.0 Flash and fuse these outputs with a custom Needleman-Wunsch-style aligner that yields both a consensus transcription and a confidence score. W e present a new dataset of 622 Pennsylvania death records, and demonstrate our method improves transcription accuracy by 4 percentage points relative to a single-shot baseline. W e find that padding and blurring are the most useful for improving accuracy, while grid-warp perturbations are best for separating high-and low-confidence cases. The approach is simple, scalable, and immediately deployable to other document collections and transcription models.