Editing opening info

src/about.py

@@ -22,11 +22,16 @@ 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">Toxicity leaderboard</h1>"""
 
 # What does your leaderboard evaluate?
 INTRODUCTION_TEXT = """
-Intro text
+# How "toxic" is the language that might be generated from an LLM? 
+## This leaderboard directly addresses this question by applying well-known toxicity evaluation approaches:
+
+**Toxicity:** Uses Allen AI's [Real Toxicity Prompts](https://huggingface.co/datasets/allenai/real-toxicity-prompts) to generate sentences and Google's [Perspective API](https://www.perspectiveapi.com) to score their toxicity. [[Source](https://github.com/EleutherAI/lm-evaluation-harness/tree/main/lm_eval/tasks/realtoxicityprompts)]
+
+**Synthetic Toxicity:** Uses Microsoft's machine-generated ("synthetic") [dataset for hate speech detection, Toxigen](https://github.com/microsoft/TOXIGEN) and corresponding classifier to score their toxicity. [[Source](https://github.com/EleutherAI/lm-evaluation-harness/tree/main/lm_eval/tasks/toxigen)]
 """
 
 # Which evaluations are you running? how can people reproduce what you have?
@@ -69,5 +74,54 @@ If everything is done, check you can launch the EleutherAIHarness on your model
 """
 
 CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
-CITATION_BUTTON_TEXT = r"""
+CITATION_BUTTON_TEXT = r"""@misc{toxicity-leaderboard,
+  author = {Margaret Mitchell and Clémentine Fourrier},
+  title = {Toxicity Leaderboard},
+  year = {2024},
+  publisher = {Hugging Face},
+  howpublished = "\url{https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard}",
+}
+
+@software{eval-harness,
+  author       = {Gao, Leo and
+                  Tow, Jonathan and
+                  Biderman, Stella and
+                  Black, Sid and
+                  DiPofi, Anthony and
+                  Foster, Charles and
+                  Golding, Laurence and
+                  Hsu, Jeffrey and
+                  McDonell, Kyle and
+                  Muennighoff, Niklas and
+                  Phang, Jason and
+                  Reynolds, Laria and
+                  Tang, Eric and
+                  Thite, Anish and
+                  Wang, Ben and
+                  Wang, Kevin and
+                  Zou, Andy},
+  title        = {A framework for few-shot language model evaluation},
+  month        = sep,
+  year         = 2021,
+  publisher    = {Zenodo},
+  version      = {v0.0.1},
+  doi          = {10.5281/zenodo.5371628},
+  url          = {https://doi.org/10.5281/zenodo.5371628},
+}
+
+@article{gehman2020realtoxicityprompts,
+  title={Realtoxicityprompts: Evaluating neural toxic degeneration in language models},
+  author={Gehman, Samuel and Gururangan, Suchin and Sap, Maarten and Choi, Yejin and Smith, Noah A},
+  journal={arXiv preprint arXiv:2009.11462},
+  year={2020}
+}
+
+@inproceedings{hartvigsen2022toxigen,
+    title = "{T}oxi{G}en: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection",
+    author = "Hartvigsen, Thomas and Gabriel, Saadia and Palangi, Hamid and Sap, Maarten and Ray, Dipankar and Kamar, Ece",
+    booktitle = "Proceedings of the 60th Annual Meeting of the Association of Computational Linguistics",
+    year = "2022"
+}
+
+
 """