multilingual
sea
nxphi47 commited on
Commit
c1861bb
·
1 Parent(s): ed7541e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -159,9 +159,9 @@ In English, our model is 46% as good as Llama-2-13b-chat, even though it did not
159
  Compared with ChatGPT-3.5, our SeaLLM-13b model is performing 45% as good as ChatGPT for Thai.
160
  For important aspects such as Safety and Task-Solving, our model is nearly on par with ChatGPT across the languages.
161
  Note that **GPT-4**, as built for global use, may not consider certain safety-related responses from ChatGPT as harmful or sensitive in the local context.
 
162
  Meanwhile, most of the safety-related questions and expected responses in this test set are globally acceptable,
163
- whereas we leave those with conflicting and controversial opinions for future human evaluation.
164
-
165
 
166
  <div class="row" style="display: flex; clear: both;">
167
  <img src="seallm_vs_chatgpt_by_lang.png" alt="Snow" style="float: left; width: 49.5%">
 
159
  Compared with ChatGPT-3.5, our SeaLLM-13b model is performing 45% as good as ChatGPT for Thai.
160
  For important aspects such as Safety and Task-Solving, our model is nearly on par with ChatGPT across the languages.
161
  Note that **GPT-4**, as built for global use, may not consider certain safety-related responses from ChatGPT as harmful or sensitive in the local context.
162
+ Using GPT-4 to evaluate ChatGPT-3.5 can also be tricky not only for safety aspects because they likely follow a similar training strategy with similar data.
163
  Meanwhile, most of the safety-related questions and expected responses in this test set are globally acceptable,
164
+ whereas we leave those with conflicting and controversial opinions, as well as more comprehensive human evaluation for future update.
 
165
 
166
  <div class="row" style="display: flex; clear: both;">
167
  <img src="seallm_vs_chatgpt_by_lang.png" alt="Snow" style="float: left; width: 49.5%">