Name That LLM
Identify the model behind the text
Official pageOpen the competition on Kaggle↗
- Effort
- 25–70 hours
- Difficulty
- Advanced
- Compute
- CPU only
- Scoring
- Automatic
At a glance
Full rules ↗- Scoring
- Balanced Accuracy Score
- Teams
- Up to 5 per team
- Submitting
- Up to 5 a day; code runs in the platform's notebooks
- Provided
- Free GPU
Is it for you?
Prepare before joining
Beginner fit24/100
Learning value69/100
The editors' notes, in Chinese; there is no English translation yet.
Who it suits
适合具备 NLP 文本分类经验、愿意研究短文本风格特征的参赛者。你需要能处理跨哲学、理工科与创作文本的模型归因任务，并在 Kaggle Notebook 中完成可复现的离线推理提交。
What makes it hard
最大难点是从仅 40–250 词、且测试提示词从未在训练集出现过的段落中区分 18 个模型；不能依赖主题词或长度等捷径。提交还必须是禁网环境下可在时限内重跑的 Notebook，并输出严格格式的 Parquet 文件。
Getting started
Skills to bring
In Chinese; there is no English translation yet.
- NLP 文本多分类
- 作者归因与风格特征
- Transformer 预训练模型
- 跨提示词泛化验证
- Kaggle Notebook
- Pandas Parquet 文件输出
We haven't pulled tutorials, data or baselines from the official page yet; the task and the data are there.
First competition? Read No GPU? Pick Competitions That Still Teach You Good Habits