-
**New Title**: Trustworthy AI: Advanced AI risk evaluation and mitigation
**New Description**: New challenges and threats are emerging as AI evolves. Learn how Azure AI’s advanced responsible AI tooli…
-
Evaluate safety issue of LLMs from various aspects
(To be continued, open by JingFeng, Hongye, ...)
-
Restructure the genAI_Eval to categorize the various Evaluation criteria. Need to have different Repos for each category so it makes it easier to users to find what they are looking for.
Example: A…
-
Create the list of the order of documents to fill in. this should follow the Design and development SOP to start with, with other QMS SOP following.
**Order to fill out Templates**
1. Literature …
-
Hi there,
Thank you for benchmarking Llama Guard 3 and sharing the learnings with us. We will continue to improve the Llama Guard series and Llama safety overall. However, I notice that there might…
JFChi updated
1 month ago
-
I am working on a project which involves the evaluation of several functions and their derivatives. At each step, the derivatives of several different functions have to be evaluated (rather than sever…
-
## Evaluation short description
- Why is this evaluation interesting?
RewardBench is perhaps the _only_ evaluation suite to provide broad coverage of the strengths and weaknesses of reward models …
-
#### Objective
To conduct a comprehensive evaluation of the existing electrical panel box to identify its current capabilities, limitations, and any necessary upgrades for the planned expansion to 42…
-
### What
- WHO/FAO JECFA Toxicity evaluation
- WHO/FAO JECFA Safety evaluation
- EFSA opinions
- FSANZ Hazard Assessment
The taxonomy has a few examples already:
https://en.wiki.openfoodfacts.…
-
Hi team,
I have tried to use GPT4 as a classifier to classify the model responses but am getting content moderation filter trigger.
Changes made -- Instead of Llama70BJudge, I have a similar cla…