Viewing profile — ritvikpandey21

We've been building table extraction at Pulse and evaluated four benchmarks: OmniDocBench, SCORE-Bench, ParseBench, and RD-TableBench. None of them fully reflect the enterprise doc…

[dead]

Results look pretty good (with the exception of one very faint page) - check it out here! https://platform.runpulse.com/dashboard/extractions/public/f...

thanks! we benchmark against all the major players (azure doc intelligence, aws textract, google doc ai, frontier llms, etc). we have some public news coming out soon on this front…

yeah models are definitely improving, but we've found even the latest ones still hallucinate and infer text rather than doing pure transcription. we carry out very rigorous benchma…

yeah models are definitely improving, but we've found even the latest ones still hallucinate and infer text rather than doing pure transcription. we carry out very rigorous benchma…

thanks for the flag! have pointed this out will be pushing an update here shortly

we disagree! we've found llms by themselves aren't enough and suffer from pretty big failure modes like hallucination and inferring text rather than pure transcription. we wrote a …

thanks! appreciate the kind words

our team has tested docling pretty extensively, works well for simpler text-heavy docs without complex layouts, but the moment you introduce tables or multi-column stuff it doesn't…

we're more focused on the core extraction layer itself rather than workflow tooling. we train our own vision models for layout detection, ocr, and table parsing from scratch. the k…

DeepSeek AI just released DeepSeek-OCR, a new open-source model that aims to rethink text extraction through what it calls Context Optical Compression. The launch quickly caught at…

interesting read

We processed hundreds of millions of pages and found that a single accuracy metric is misleading. A model that's 98% accurate on 1,000 pages with 200 data elements each still produ…

We evaluated ByteDance's Dolphin document parsing model on enterprise document processing tasks using standardized benchmarks and real-world document sets. Our testing dataset incl…

After processing nearly 500 million pages of enterprise documents, we've discovered that the biggest challenge in document AI isn't character recognition or table extraction. It's …

[flagged]

curious how LLM hallucinations will work on logging info - gonna be a hard problem to solve