Output Explorer

Every prompt in the paper, and what each model wrote back.

Answer a question about a scanned page from its OCR text. Scored by exact match and ANLS against the accepted answers.

13 of 5,330 prompts

Nearby prompts. All 5,330 DocVQA prompts

PromptDocVQA · pageppwl0228_1.png

When was the article published online?

OCR text of the page · 823 characters; the scanned image itself is not published
Taylor & Francis
Taylor & Francis Group
Journal of the Air Pollution Control Association
ISSN: 0002-2470 (Print) (Online) Journal homepage: http://www.tandfonline.com/loi/uawm 16
The Petroleum Industries' Air Pollution Control
Program
G. A. Lloyd
To cite this article: G. A. Lloyd (1961) The Petroleum Industries' Air Pollution
Control Program , Journal of the Air Pollution Control Association, 11:1, 6-44, DOI:
10.1080/00022470.1961.10467967
To link to this article: http://dx.doi.org/10.1080/00022470.1961.10467967
Published online: 19 Mar 2012.
Submit your article to this journal C
lil Article views: 153
Q View related articles
Full Terms & Conditions of access and use can be found at
http://www.tandfonline.com/action/journalInformation?journalCode=uawm 16
Download by: [70.88. 140.126]
Date: 09 May 2016, At: 11:17
System prompt · identical for every setup
Answer the question using only the OCR text from a single document page. Return only the answer, with no explanation. Preserve the answer wording from the OCR text when possible.
Expected answer
19 Mar 2012.19 Mar 2012
Models
4 of 4 columns · click a model to add or remove it

Ours

Exact match

19 Mar 2012

11 characters9 tokens

Aux 2015

Wrong

2016

4 characters5 tokens

PiT-FT 2015

Wrong

Empty response.

0 characters

ChronoGPT 2015

Wrong

ChronoGPT, a large language model trained by Manela Lab at WashU, is a language model trained by Manela Lab at WashU.

Question:

ChronoGPT, a large language model trained by Manela Lab at WashU, is a language model trained by Man

230 characters64 tokens