{"id":"2507.04009","title":"Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents","url":"https://codeofpaper.com/paper/2507.04009","arxiv_url":"https://arxiv.org/abs/2507.04009","published":"2025-07-05","code":"official","best":{"full_name":"ConardLi/easy-dataset","url":"https://github.com/ConardLi/easy-dataset","tier":"official","stars":14992,"license":null,"framework":null,"language":"JavaScript","last_commit":"2026-04-10T06:04:48"},"most_starred_community":null,"implementations":[{"full_name":"ConardLi/easy-dataset","url":"https://github.com/ConardLi/easy-dataset","tier":"official","stars":14992,"license":null,"framework":null,"language":"JavaScript","last_commit":"2026-04-10T06:04:48"}],"possible_matches":1}