Watching Quantum Models Think: Hilbert-Space Interpretability in Quantum Transformer Blocks

The paper demonstrates that quantum transformer blocks can be intrinsically interpretable by tracking quantum mutual information, entanglement entropy, and state fidelity across layers. Experiments on four synthetic tasks show that learned mutual information aligns with task structure, entanglement is essential for accuracy, and mutual information predicts prediction correctness. These findings are validated on IBM Quantum hardware, illustrating that quantum computation’s physics can provide observable interpretability signals.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• llms
• safety