Popular repositories Loading

2. In-context Example Selection with Influences

   Python 15 1

3. An agent for auditing repositories of traces for violations of safety properties. Automatically finds cheating (task-level gaming and harness-level cheating) on top benchmarks.

   Python 15 3

4. Instruction Following by Boosting Attention of Large Language Models

   Jupyter Notebook 8 1

5. Official repository for "Probabilistic Soundness Guarantees in LLM Reasoning Chains"

   Jupyter Notebook 6 1

Repositories