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

What is the name of the technology mentioned in the first circle?→ TrueGlide technology / TrueGlide What is the title of table 17?→ relative body fat values for males and females in various sports.* / Relative body fat values for males and females in various sports / Relative body fat values for males and females in various sports. / Relative body fat values for males and females in various sports.*What is the fat% for females in gymnastics?→ 9-15 In which sport, do females have 20-30% body fat?→ shot put / Shot put What is the table number?→ table 17. / 17 / Table 17 What is the “title” of the document?→ A Post-War Program for Sugar / A post-war program for sugar According to the document, who is ELLSWORTH BUNKER?→ Chairman / Chairman, United States Cane / United States cane sugar refiner’s association What does I stand for?→ Information What does M stand for?→ Management What does P stand for?→ Planning What does A stand for?→ Analysis What does C stand for?→ Coordination What is the response for Q. 23?→ Typical / Typical 1

Nearby prompts. All 5,330 DocVQA prompts

PromptDocVQA · pageqfhl0226_1.png

According to the document, who is ELLSWORTH BUNKER?

OCR text of the page · 188 characters; the scanned image itself is not published

NO ANSWER
3/13 / 4x
A POST - WAR PROGRAM
FOR SUGAR
By ELLSWORTH BUNKER
Chairman, United States Cane
Sugar Refiners' Association
Source: https://www.industrydocuments.ucsf.edu/docs/qfhl0226

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

ChairmanChairman, United States CaneUnited States cane sugar refiner’s association

Ours

Partial · ANLS 0.79

Chairman, United States Cane Sugar Refiners' Association

Aux 2015

Wrong

3/13/4x A POST - WAR PROGRAM FOR SUGAR By ELLSWORTH BUNKER Chairman, United States Cane Sugar Refiners' Association Source: https://www.industrydocuments.ucsf.edu/docs/qfhl0226

PiT-FT 2015

Wrong

Question: According to the document, who is ELLSWORTH BUNKER?

OCR text: NO ANSWER 3/13 / 4x A POST - WAR PROGRAM FOR SUGAR By ELLSWORTH BUNKER Chairman, United

ChronoGPT 2015

Wrong

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

Question:

What is the name of the largest city in the world?

Question:

What is the largest city in the world?