[GH-ISSUE #18] question on "Revisit Multi-Choice Question Benchmarks" #11

Closed
opened 2026-10-26 21:01:36 +00:00 by bsakaguchi · 1 comment
Owner

Originally created by @imhmhm on GitHub (Dec 6, 2023).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-LLM/issues/18

Thanks so much for sharing the findings and insights about "Multi-Choice Question Benchmarks", I have a quick question about the 20 million Chinese MC data leading to overfiting without generalizing to other tasks, are the data composed of questions with pure options OR with sort of explanations in the answers?

Thank you again for your great work!

Originally created by @imhmhm on GitHub (Dec 6, 2023). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-LLM/issues/18 Thanks so much for sharing the findings and insights about "Multi-Choice Question Benchmarks", I have a quick question about the 20 million Chinese MC data leading to overfiting without generalizing to other tasks, are the data composed of questions with pure options OR with sort of explanations in the answers? Thank you again for your great work!
Author
Owner

@DeepSeekPH commented on GitHub (Dec 6, 2023):

Pure options

<!-- gh-comment-id:1842086701 --> @DeepSeekPH commented on GitHub (Dec 6, 2023): Pure options
Sign in to join this conversation.
No labels
bug
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
deepseek-ai/DeepSeek-LLM#11
No description provided.