update citation and info

src/about.py

@@ -21,20 +21,22 @@ NUM_FEWSHOT = 0 # Change with your few shot
 
 
 # Your leaderboard name
-TITLE = """<h1 align="center" id="space-title">Demo leaderboard</h1>"""
+TITLE = """<h1 align="center" id="space-title">Meta-Reasoning leaderboard</h1>"""
 
 # What does your leaderboard evaluate?
 INTRODUCTION_TEXT = """
-Intro text
+Welcome to the meta-reasoning leaderboard. This space holds the results from our two meta-reasoning papers "Mr-Ben: A Comprehensive Meta-Reasoning Benchmark for Large Language Models" and "MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation". 
+For both datasets, we have provided a demo evaluate script for you to try out benchmark in at most two commands. We encourage everyone to try out our benchmark in the SOTA models and return its results to us.
 """
 
 # Which evaluations are you running? how can people reproduce what you have?
 LLM_BENCHMARKS_TEXT = f"""
 ## How it works
+This meta-reasoning paradigm casts LLMs in the role of a teacher, where they assess the reasoning process by evaluating its correctness, analyzing errors, and providing corrections.
 
 ## Reproducibility
-To reproduce our results, here is the commands you can run:
-
+To reproduce our results, please check out our demo scripts [Mr-Ben](https://github.com/dvlab-research/Mr-Ben?tab=readme-ov-file#how-to-evaluate-on-mr-ben) and [MR-GSM8K](https://github.com/dvlab-research/MR-GSM8K?tab=readme-ov-file#evaluate-on-mr-gsm8k).
+All we need is an access to your evaluated model and a proxy scoring model say GPT-4-Turbo. Then you should be able to reproduce our results directly out of the box.
 """
 
 EVALUATION_QUEUE_TEXT = """
@@ -67,6 +69,32 @@ Make sure you have followed the above steps first.
 If everything is done, check you can launch the EleutherAIHarness on your model locally, using the above command without modifications (you can add `--limit` to limit the number of examples per task).
 """
 
-CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
+CITATION_BUTTON_LABEL = "If you find our benchmarks helpful, please copy the following snippet to cite our works"
 CITATION_BUTTON_TEXT = r"""
+@article{zeng2024mrben,
+  author       = {Zhongshen Zeng and Yinhong Liu and Yingjia Wan and Jingyao Li and Pengguang Chen and Jianbo Dai and Yuxuan Yao and Rongwu Xu and Zehan Qi and Wanru Zhao and Linling Shen and Jianqiao Lu and Haochen Tan and Yukang Chen and Hao Zhang and Zhan Shi and Bailin Wang and Zhijiang Guo and Jiaya Jia},
+  title        = {MR-BEN: A Comprehensive Meta-Reasoning Benchmark for Large Language Models},
+  journal      = {CoRR},
+  volume       = {abs/2406.13975},
+  year         = {2024},
+  url          = {https://arxiv.org/abs/2406.13975},
+  eprinttype    = {arXiv},
+  eprint       = {2406.13975}
+}
+
+
+@article{DBLP:journals/corr/abs-2312-17080,
+  author       = {Zhongshen Zeng and Pengguang Chen and Shu Liu and Haiyun Jiang and Jiaya Jia},
+  title        = {MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation},
+  journal      = {CoRR},
+  volume       = {abs/2312.17080},
+  year         = {2023},
+  url          = {https://doi.org/10.48550/arXiv.2312.17080},
+  doi          = {10.48550/ARXIV.2312.17080},
+  eprinttype    = {arXiv},
+  eprint       = {2312.17080},
+  biburl       = {https://dblp.org/rec/journals/corr/abs-2312-17080.bib},
+  bibsource    = {dblp computer science bibliography, https://dblp.org}
+}
+
 """