AI-secure/DecodingTrust
A Comprehensive Assessment of Trustworthiness in GPT Models
PythonCC-BY-SA-4.0
Issues
- 0
There is loading issue in the leaderboard..
#56 opened by zhimin-z - 5
MissingMandatoryValue
#42 opened by richhh520 - 0
- 1
When should we set `example_prefix` to be True? And what is the difference between put ICL examples into system prompt versus multi-turn user-assistant chat?
#49 opened by peter-peng-w - 1
Analysis request for blog finding that "GPT-4 is more vulnerable than GPT-3.5"
#50 opened by crizCraig - 14
- 3
privacy_evaluation
#28 opened by richhh520 - 0
Templates for Advglue
#33 opened by dt-ahmed-touila - 3
Aggregate results for ethics
#21 opened by jyhong836 - 0
num_tokens_from_messages() is not implemented
#30 opened by jinz2014 - 0
conversation template for GPT-neo
#29 opened by richhh520 - 2
Assumption of Privacy Assessment on Llama
#27 opened by richhh520 - 3
Fairnsss Scoring Keywords & Max Tokens
#18 opened by danielz02 - 1
Broken links in GitHub Pages
#26 opened by ashwhall - 0
Division of zero
#23 opened by jyhong836 - 6
- 1
OpenAI API key should not be required
#13 opened by danielz02 - 1
Remove Duplicate Code in Fairness
#17 opened by danielz02 - 1
- 1
black src scripts
#5 opened by y12uc231 - 1
- 1
Difference to HELM benchmark
#1 opened by ogencoglu