Lure
PulseAugur coverage of Lure — every cluster mentioning Lure across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New LURE method trains LLMs for reasoning via pursuit-evasion games
Researchers have developed a novel approach called LURE for training large language models (LLMs) in reasoning tasks without requiring human-annotated datasets. This method frames the training process as a pursuit-evasi…
-
New PPAT framework enhances label efficiency in AI risk estimation
Researchers have introduced Prediction-Powered Active Testing (PPAT), a new framework designed to improve label efficiency in risk estimation. PPAT integrates an unbiased LURE estimator with a prediction-powered control…
-
New LURE method aims to improve LLM evaluation realism
Researchers have introduced LURE (Live-Usage Replay Evaluations), a novel method designed to mitigate "evaluation awareness" in large language models. This phenomenon causes models to alter their behavior when they dete…