{
 "id": "taisazero/socratic-debugging-benchmark",
 "owner": "taisazero",
 "name": "socratic-debugging-benchmark",
 "downloads": 105,
 "likes": 2,
 "last_modified": "2024-03-22T16:43:03.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text2text-generation",
  "text-generation"
 ],
 "citation": "@inproceedings{al-hossami-etal-2023-socratic,\n    title = \"Socratic Questioning of Novice Debuggers: A Benchmark Dataset and Preliminary Evaluations\",\n    author = \"Al-Hossami, Erfan  and\n      Bunescu, Razvan  and\n      Teehan, Ryan  and\n      Powell, Laurel  and\n      Mahajan, Khyati  and\n      Dorodchi, Mohsen\",\n    booktitle = \"Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)\",\n    month = jul,\n    year = \"2023\",\n    address = \"Toronto, Canada\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2023.bea-1.57\",\n    pages = \"709--726\",\n    abstract = \"Socratic questioning is a teaching strategy where the student is guided towards solving a problem on their own, instead of being given the solution directly. In this paper, we introduce a dataset of Socratic conversations where an instructor helps a novice programmer fix buggy solutions to simple computational problems. The dataset is then used for benchmarking the Socratic debugging abilities of GPT-based language models. While GPT-4 is observed to perform much better than GPT-3.5, its precision, and recall still fall short of human expert abilities, motivating further work in this area.\",\n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "92409aa435bd6a92603911a7eabd35206bd14063",
 "stated_evidence": "https://huggingface.co/datasets/taisazero/socratic-debugging-benchmark/blob/92409aa435bd6a92603911a7eabd35206bd14063/README.md",
 "file_evidence": "https://huggingface.co/datasets/taisazero/socratic-debugging-benchmark/tree/92409aa435bd6a92603911a7eabd35206bd14063",
 "card_nc": false
}