You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+3-31Lines changed: 3 additions & 31 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -6,13 +6,6 @@ To automate the evaluation process, we prompt strong LLMs like GPT-4 to act as j
6
6
7
7
To be clarified, such zero-shot QA-style evaluation might be more suitable for those LLMs that have been fine-tuned with instructions. The 80 questions are manually translated from the English Vicuna benchmark.
8
8
9
-
## Contents
10
-
-[Install](#install)
11
-
-[Evaluate a model with Japanese Vicuna QA Benchmark](#evaluate-a-model-with-japanese-vicuna-qa-benchmark)
12
-
-[Sample Outputs](#sample-outputs)
13
-
-[An Example of pairwise win-rate of three Japanese LLMs](#pairwise-win-rate-of-three-japanese-llms)
0 commit comments