Pinned Loading

1. MisleadLM MisleadLM Public

   Forked from Jiaxin-Wen/MisleadLM

   A re-implementation and extension of the code of the paper: "Language Models Learn to Mislead Humans via RLHF""

   Python

2. Targeted-Manipulation-and-Deception-in-LLMs Targeted-Manipulation-and-Deception-in-LLMs Public

   Forked from marcus-jw/Targeted-Manipulation-and-Deception-in-LLMs

   A benchmark for evaluating the tendency of LLM agents to influence human preferences

   Python

3. rl-testing-experiments rl-testing-experiments Public

   Python 1

4. ethz-spylab/superhuman-ai-consistency ethz-spylab/superhuman-ai-consistency Public

   Python 30 2