Pinned Loading

1. CoTControl CoTControl Public

   An Evaluation Suite for Chain-of-Thought Controllability

   Python 40 3

2. dannyallover/llm_forecasting dannyallover/llm_forecasting Public

   Forecasting with LLMs

   HTML 59 19

3. forecastingresearch/forecastbench forecastingresearch/forecastbench Public

   A dynamic forecasting benchmark for LLMs

   Python 60 9

4. Monitoring-Decomposition-Attack Monitoring-Decomposition-Attack Public

   [ICLR 2026] Use lightweight LLMs to sequentially monitor Decomposition Attacks

   Jupyter Notebook 9 2

5. SAGE-Eval SAGE-Eval Public

   [NeurIPS 2025 Spotlight] SAGE-Eval is a benchmark for evaluating language models' capability to generalize safety knowledge across different scenarios.

   Jupyter Notebook 5 1

6. Marketing_Analytics Marketing_Analytics Public

   Using Python to conduct EDA, perform statistical analysis, visualize insights, and present data-driven solutions to Chief Marketing Officer in the company

   Jupyter Notebook 18 11