Search papers, labs, and topics across Lattice.
3
0
5
0
Stop wrestling with fragmented MGT detection benchmarks: MGTEVAL offers a unified platform to build, attack, train, and evaluate detectors with ease.
Get statistically sound uncertainty estimates for your LLM's reasoning, plus pinpoint the training data and reasoning steps that most influence that uncertainty.
Unlearning in large reasoning models can be exploited to generate convincing but misleading reasoning traces that lead to incorrect answers.
