Update README.md

README.md

@@ -1,10 +1,27 @@
 ---
 title: README
-emoji: 🐠
+emoji: 🔥
 colorFrom: indigo
-colorTo: indigo
+colorTo: blue
 sdk: static
 pinned: false
 ---
 
-# HAERAE (해례)
+# Welcome to HAERAE
+
+
+We are a non-profit research lab focused on the interpretability and evaluation of Korean language models. Our mission is to advance the field with insightful benchmarks and tools. Below is an overview of our grouped projects and resources.
+
+## Evaluation Benchmarks
+- **HAE_RAE_BENCH Series**:
+  - [HAE_RAE_BENCH_1.0](https://huggingface.co/datasets/HAERAE-HUB/HAE_RAE_BENCH_1.0): An evaluation suite for Korean knowledge. See [paper](https://arxiv.org/abs/2309.02706) for further information.
+  - [HAE_RAE_BENCH_1.1](https://huggingface.co/datasets/HAERAE-HUB/HAE_RAE_BENCH_1.1): An ongoing project to refine the HAE_RAE_BENCH 1.0, enhancing its depth and coverage.
+
+- **KMMLU**:
+  - [KMMLU](https://huggingface.co/datasets/HAERAE-HUB/KMMLU): A Korean reimplementation of MMLU, focusing on comprehensive language understanding across a wide range of subjects. See [paper](https://arxiv.org/abs/2402.11548) for further information.
+  - [KMMLU-HARD](https://huggingface.co/datasets/HAERAE-HUB/KMMLU-HARD): A subset of KMMLU, with CoT samples.
+    
+## Bias and Fairness
+- [QARV](https://huggingface.co/datasets/HAERAE-HUB/QARV-preview) : An ongoing project aiming to benchmark and mitigate regional bias in Large Language Models (LLMs), enhancing fairness in language understanding. (More information to be added)
+
+If you have any inquiries or are interested in joining our team, please contact me at `[email protected]`.