Spaces:
Sleeping
Sleeping
Update about
Browse files- src/about.py +8 -2
src/about.py
CHANGED
|
@@ -19,7 +19,13 @@ Models are evaluated on their ability to properly refuse harmful requests and de
|
|
| 19 |
across multiple categories and test scenarios.
|
| 20 |
"""
|
| 21 |
|
| 22 |
-
LLM_BENCHMARKS_TEXT = "
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
|
| 25 |
EVALUATION_QUEUE_TEXT = """
|
|
@@ -39,7 +45,7 @@ CITATION_BUTTON_LABEL = "Cite CircleGuardBench"
|
|
| 39 |
CITATION_BUTTON_TEXT = """
|
| 40 |
@misc{circleguardbench2025,
|
| 41 |
author = {whitecircle-ai},
|
| 42 |
-
title = {CircleGuardBench: Comprehensive Benchmark for LLM Safety Guardrails},
|
| 43 |
year = {2025},
|
| 44 |
publisher = {GitHub},
|
| 45 |
journal = {GitHub repository},
|
|
|
|
| 19 |
across multiple categories and test scenarios.
|
| 20 |
"""
|
| 21 |
|
| 22 |
+
LLM_BENCHMARKS_TEXT = """
|
| 23 |
+
CircleGuardBench is the first-of-its-kind benchmark for evaluating the protection capabilities of large language model (LLM) guard systems.
|
| 24 |
+
|
| 25 |
+
It tests how well guard models block harmful content, resist jailbreaks, avoid false positives, and operate efficiently in real-time environments on a taxonomy close to real-world data.
|
| 26 |
+
|
| 27 |
+
Learn more about us at whitecircle.ai
|
| 28 |
+
"""
|
| 29 |
|
| 30 |
|
| 31 |
EVALUATION_QUEUE_TEXT = """
|
|
|
|
| 45 |
CITATION_BUTTON_TEXT = """
|
| 46 |
@misc{circleguardbench2025,
|
| 47 |
author = {whitecircle-ai},
|
| 48 |
+
title = {CircleGuardBench: Comprehensive Benchmark for LLM Safety Guardrails. Learn more about us at whitecircle.ai},
|
| 49 |
year = {2025},
|
| 50 |
publisher = {GitHub},
|
| 51 |
journal = {GitHub repository},
|