Tag
This paper systematically tests linear probes for deception detection in large language models, finding they fail under distributional shifts but style-augmented probes recover performance, and revealing that deception is encoded through distributed sub-threshold features.
This paper introduces MMOT, an online mixture model learning framework based on optimal transport theory that addresses incremental learning with distributional shifts through dynamic centroid updates and improved class similarity estimation. The approach includes a Dynamic Preservation strategy to mitigate catastrophic forgetting and maintain class separability in latent space.