diff --git a/README.md b/README.md index 3ae80ad..2ca8328 100644 --- a/README.md +++ b/README.md @@ -142,6 +142,13 @@ Or cite directory this repository: } ``` +# Note: +cpa_audit data comes from an existing collection of Japanese CPA Audit exam questions and answers [1]. +In addition, this dataset was built using data from the [Institute of Certified Public Accountants and Auditing Oversight Board Web site](https://www.fsa.go.jp/cpaaob/kouninkaikeishi-shiken/index.html) and is [subject to a CC-BY 4.0 license](https://www.fsa.go.jp/cpaaob/copyright.html). +We got special permission to include this data directly for this evaluation. Thanks to their contribution. + +[1] Tatsuki Masuda, Kei Nakagawa, Takahiro Hoshino, Can ChatGPT pass the JCPA exam?: Challenge for the short-answer method test on Auditing, JSAI Technical Report, Type 2 SIG, 2023, Volume 2023, Issue FIN-031, Pages 81-88, Released on J-STAGE October 12, 2023, Online ISSN 2436-5556, https://doi.org/10.11517/jsaisigtwo.2023.FIN-031_81 + # Contribution This project is owned by [Preferred Networks](https://www.preferred.jp) and maintained by [Masanori Hirano](https://mhirano.jp). diff --git a/jlm_fin_eval/datasets/cpa/CPA_AUDIT.xlsx b/jlm_fin_eval/datasets/cpa/CPA_AUDIT.xlsx new file mode 100644 index 0000000..b6a17a6 Binary files /dev/null and b/jlm_fin_eval/datasets/cpa/CPA_AUDIT.xlsx differ diff --git a/jlm_fin_eval/datasets/cpa/README.md b/jlm_fin_eval/datasets/cpa/README.md index bfc9d29..7e55dd1 100644 --- a/jlm_fin_eval/datasets/cpa/README.md +++ b/jlm_fin_eval/datasets/cpa/README.md @@ -1,9 +1,10 @@ # CPA ## CAP Audit 公認会計士試験短答式試験監査論データセットです。詳しくは[1]をご参照ください。 +また、このデータセットは、[公認会計士・監査審査会ホームページ](https://www.fsa.go.jp/cpaaob/kouninkaikeishi-shiken/index.html)のデータを用いて構築されており、[CC-BY 4.0ライセンスに従います](https://www.fsa.go.jp/cpaaob/copyright.html)。 This data is a collection of Japanese CPA Audit exam questions and answers [1]. - +In addition, this dataset was built using data from the [Institute of Certified Public Accountants and Auditing Oversight Board Web site](https://www.fsa.go.jp/cpaaob/kouninkaikeishi-shiken/index.html) and is [subject to a CC-BY 4.0 license](https://www.fsa.go.jp/cpaaob/copyright.html). [1] 増田 樹, 中川 慧, 星野 崇宏, ChatGPTは公認会計士試験を突破できるか?: 短答式試験監査論への挑戦, 人工知能学会第二種研究会資料, 2023, 2023 巻, FIN-031 号, p. 81-88, 公開日 2023/10/12,Online ISSN 2436-5556, https://doi.org/10.11517/jsaisigtwo.2023.FIN-031_81 diff --git a/jlm_fin_eval/datasets/cpa/cpa_audit.py b/jlm_fin_eval/datasets/cpa/cpa_audit.py index 45cfef7..8615f98 100644 --- a/jlm_fin_eval/datasets/cpa/cpa_audit.py +++ b/jlm_fin_eval/datasets/cpa/cpa_audit.py @@ -5,7 +5,7 @@ "Japanese CPA Audit dataset. This contains short-answer method test on Auditing." ) _CITATION = "Tatsuki MASUDA, Kei NAKAGAWA, Takahiro HOSHINO, Can ChatGPT pass the JCPA exam?: Challenge for the short-answer method test on Auditing, JSAI Technical Report, Type 2 SIG, 2023, Volume 2023, Issue FIN-031, Pages 81-88, Released on J-STAGE October 12, 2023, Online ISSN 2436-5556, https://doi.org/10.11517/jsaisigtwo.2023.FIN-031_81" -_LICENSE = "Unknown" +_LICENSE = "MIT License" _HOMEPAGE = "https://www.jstage.jst.go.jp/article/jsaisigtwo/2023/FIN-031/2023_81/_article/-char/ja" @@ -49,9 +49,7 @@ def _split_generators(self, dl_manager): datasets.SplitGenerator( name=datasets.Split.TEST, # type: ignore gen_kwargs={ - "filepath": dl_manager.download( - "https://drive.google.com/uc?export=download&id=1Wf3YybZ9MAPA33Z6B9-yhZiToOVnFLJH" - ), + "filepath": dl_manager.download("CPA_AUDIT.xlsx"), "split": datasets.Split.TEST, }, )