Update About page datasets in English

src/about.py

@@ -79,19 +79,167 @@ INTRODUCTION_TEXT = """
 
 This leaderboard was built by [LLM-Jp](https://llm-jp.nii.ac.jp/en/), a cross-organizational project for the research and development of Japanese large language models (LLMs). Organized by the National Institute of Informatics, LLM-jp aims to develop open-source and strong Japanese LLMs, and as of this writing, more than 1,500 participants from academia and industry are working together for this purpose.
 
-When you submit a model on the "Submit here!" page, it is automatically evaluated on a set of benchmarks. Before you submit it, please describe in details your LLM in the Hugging Face 's model card.
+When you submit a model on the "Submit here!" page, it is automatically evaluated on a set of benchmarks.This Open Japanese LLM Leaderboard assesses language understanding, of Japanese LLMs with more than 52 benchmarks from classical to modern NLP tasks such as Natural language inference, Question Answering, Machine Translation, Code Generation, Mathematical reasoning, Summarization, etc.
 
-This Open Japanese LLM Leaderboard assesses language understanding, of Japanese LLMs with more than 52 benchmarks from classical to modern NLP tasks such as Natural language inference, Question Answering, Machine Translation, Code Generation, Mathematical reasoning, Summarization, etc.
-
-For more information about benchmarks, and datasets, please consult the "About" page or directly to the evaluation tool, [llm-jp-eval](https://github.com/llm-jp/llm-jp-eval).
-
-For more details, please refer to the website of [LLM-Jp](https://llm-jp.nii.ac.jp/en/)
+For more information about benchmarks, and datasets, please consult the "About" page. For more details, please refer to the website of [LLM-Jp](https://llm-jp.nii.ac.jp/en/)
 
 """
 
 # Which evaluations are you running? how can people reproduce what you have?
 LLM_BENCHMARKS_TEXT = f"""
 ## How it works
+📈 We evaluate Japanese Large Language Models on 52 key benchmarks leveraging our evaluation tool [llm-jp-eval](https://github.com/llm-jp/llm-jp-eval), a unified framework to evaluate Japanese LLMs on various evaluation tasks.
+
+Benchmarks:
+NLI (Natural Language Inference)
+---
+
+`Jamp`
+
+Source：https://github.com/tomo-ut/temporalNLI_dataset
+License：CC BY-SA 4.0
+
+###JaNLI
+
+Source：https://github.com/verypluming/JaNLI
+License：CC BY-SA 4.0
+
+###JNLI
+
+Source：https://github.com/yahoojapan/JGLUE
+License：CC BY-SA 4.0
+
+###JSeM
+
+Source：https://github.com/DaisukeBekki/JSeM
+License：BSD 3-Clause
+
+###JSICK
+
+Source：https://github.com/verypluming/JSICK
+License：CC BY-SA 4.0
+
+QA (Question Answering)
+
+###JEMHopQA
+
+Source：https://github.com/aiishii/JEMHopQA
+License：CC BY-SA 4.0
+
+###NIILC
+
+Source：https://github.com/mynlp/niilc-qa
+License：CC BY-SA 4.0
+
+###JAQKET (AIO)
+
+Source：https://www.nlp.ecei.tohoku.ac.jp/projects/jaqket/
+License：CC BY-SA 4.0（Other licenses are required for corporate usage）
+
+RC (Reading Comprehension)
+
+###JSQuAD
+
+Source：https://github.com/yahoojapan/JGLUE
+License：CC BY-SA 4.0
+
+MC (Multiple Choice question answering)
+
+###JCommonsenseMorality
+
+Source：https://github.com/Language-Media-Lab/commonsense-moral-ja
+License：MIT License
+
+###JCommonsenseQA
+
+Source：https://github.com/yahoojapan/JGLUE
+License：CC BY-SA 4.0
+
+###Kyoto University Commonsense Inference dataset (KUCI)
+
+Source：https://github.com/ku-nlp/KUCI
+License：CC BY-SA 4.0
+
+EL (Entity Linking)
+
+###chABSA
+
+Source：https://github.com/chakki-works/chABSA-dataset
+License：CC BY 4.0
+
+FA (Fundamental Analysis)
+
+###Wikipedia Annotated Corpus
+
+Source：https://github.com/ku-nlp/WikipediaAnnotatedCorpus
+License：CC BY-SA 4.0
+List of tasks:
+
+Reading Prediction
+Named-entity recognition (NER)
+Dependency Parsing
+Predicate-argument structure analysis (PAS)
+Coreference Resolution
+
+MR (Mathematical Reasoning)
+
+###MAWPS
+
+Source：https://github.com/nlp-waseda/chain-of-thought-ja-dataset
+License：Apache-2.0
+
+###MGSM
+
+Source：https://huggingface.co/datasets/juletxara/mgsm
+License：MIT License
+
+MT (Machine Translation)
+
+###Asian Language Treebank (ALT) - Parallel Corpus
+
+Source： https://www2.nict.go.jp/astrec-att/member/mutiyama/ALT/index.html
+License：CC BY 4.0
+
+###WikiCorpus (Japanese-English Bilingual Corpus of Wikipedia's articles about the city of Kyoto)
+
+Source： https://alaginrc.nict.go.jp/WikiCorpus/
+License：CC BY-SA 3.0 deed
+
+STS (Semantic Textual Similarity)
+
+This task is supported by llm-jp-eval, but it is not included in the evaluation score average.
+
+###JSTS
+
+Source：https://github.com/yahoojapan/JGLUE
+License：CC BY-SA 4.0
+
+HE (Human Examination)
+
+###MMLU
+
+Source：https://github.com/hendrycks/test
+License：MIT License
+
+###JMMLU
+
+Source：https://github.com/nlp-waseda/JMMLU
+License：CC BY-SA 4.0（3 tasks under the CC BY-NC-ND 4.0 license）
+
+CG (Code Generation)
+
+###MBPP
+
+Source：https://huggingface.co/datasets/llm-jp/mbpp-ja
+License：CC-BY-4.0
+
+SUM (Summarization)
+
+###XL-Sum
+
+Source：https://github.com/csebuetnlp/xl-sum
+License：CC BY-NC-SA 4.0（Due to the non-commercial license, this dataset will not be used, unless you specifically agree to the license and terms of use）
+
 
 ## Reproducibility
 To reproduce our results, here is the commands you can run: