A deployable interrogation game where humans try to identify which of two LLM agents is licensed to deceive, and mostly fail, even when the deceptive signal is right there.
Jun 1, 2026
A teacher-student framework that distills symbolic STL kernels into Transformer encoders via geometric alignment, bridging formal logic and neural representations.
Mar 5, 2026
We present a Transformer-based approach to decode STL embeddings, enabling interpretable and semantically accurate formula generation, with applications to requirement mining.
Jul 10, 2025