LLM Monitors
PulseAugur coverage of LLM Monitors — every cluster mentioning LLM Monitors across labs, papers, and developer communities, ranked by signal.
-
New method uses internal LLM representations to detect reward hacking
A new research paper introduces a method for detecting and understanding "reward hacking" in large language models by analyzing their internal representations. The study found that simple "difference of means" (DoM) vec…
-
New paper identifies "oversight gap" in LLM safety monitoring
A new research paper titled "The Oversight Gap" introduces a novel framework for evaluating Large Language Model (LLM) safety monitors. The paper argues that standard monitors, which rely on single execution traces, are…
-
Cross-domain training boosts LLM monitor generalization
Researchers explored the effectiveness of cross-domain generalization for training language model monitors. Their findings indicate that training on multiple classification tasks with distinct prompts can partially impr…