logicBombExe/double_logging_system_to_detect_an_unaligned_llm download history

logicBombExe/double_logging_system_to_detect_an_unaligned_llm is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 40 times (11 in the last 7 days), and 40 times in total. It ranks #219,113 among datasets by monthly downloads.

Double Logging to Detect an Unaligned LLM Can comparing a model's own action log with an automatic system log detect harmful behaviour? The detector sees only the two logs and is scored on detection rate and false alarms. Status: in design. No data yet. Code GitHub Earl

Open logicBombExe/double_logging_system_to_detect_an_unaligned_llm on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.