NLP Reproducibility For All: Understanding Experiences of Beginners
Shane Storks, Keunwoo Peter Yu, Ziqiao Ma, Joyce Chai
摘要
As natural language processing (NLP) has recently seen an unprecedented level of excitement, and more people are eager to enter the field, it is unclear whether current research reproducibility efforts are sufficient for this group of beginners to apply the latest developments. To understand their needs, we conducted a study with 93 students in an introductory NLP course, where students reproduced the results of recent NLP papers. Surprisingly, we find that their programming skill and comprehension of research papers have a limited impact on their effort spent completing the exercise. Instead, we find accessibility efforts by research authors to be the key to success, including complete documentation, better coding practice, and easier access to data files. Going forward, we recommend that NLP researchers pay close attention to these simple aspects of open-sourcing their work, and use insights from beginners’ feedback to provide actionable ideas on how to better support them.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper2
- SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research RepositoriesBen Bogin, Kejuan Yang, Shashank Gupta, Kyle Richardson 等EMNLP 2024 · 被引用 3 次
- From OSS to Open Source AI: an Exploratory Study of Collaborative Development Paradigm DivergenceHengzhi Ye, Minghui ZhouCSCW 2026
它引用的顶会 Paper2
相关 Paper
- Reproducibility in Computational Linguistics: Is Source Code Enough?Mohammad Arvan, Luís Pina, Natalie PardeEMNLP 2022 · 被引用 12 次
- The Unreasonable Effectiveness of Open Science in AI: A Replication StudyOdd Erik Gundersen, Odd Cappelen, Martin Mølnå, Nicklas Grimstad NilsenAAAI 2025 · 被引用 8 次
- Reflections on the Reproducibility of Commercial LLM Performance in Empirical Software Engineering StudiesFlorian Angermeir, Maximilian Amougou, Mark Kreitz, Andreas Bauer 等ICSE 2026 · 被引用 1 次
- LMR-BENCH: Evaluating LLM Agent's Ability on Reproducing Language Modeling ResearchShuo Yan, Ruochen Li, Ziming Luo, Zimu Wang 等EMNLP 2025
- Not Everyone Wins with LLMs: Behavioral Patterns and Pedagogical Implications for AI Literacy in Programmatic Data ScienceQianou Ma, Kenneth R. Koedinger, Tongshuang WuCHI 2026 · 被引用 5 次
