Reading Why: Born-Measured Attention with Exact Word Evidence on Light and Qubits
quant-ph, cs.CL, cs.LG, physics.optics
Submitted: 2026-11-03
Updated: 2026-11-12
Code: https://github.com/stein-research/reading-why
Terminology
Sources
- Attention is not Explanation
- Attention is not not Explanation
- Seeing Why: Exact Evidence Maps for Quantum and Optical Image Classifiers
- Axiomatic Attribution for Deep Networks
- PolySketchFormer: Fast Transformers via Sketching Polynomial Kernels
- Attention Is All You Need
- Four Axiomatic Characterizations of the Integrated Gradients Attribution Method
- A large annotated corpus for learning natural language inference
- e-SNLI: Natural Language Inference with Natural Language Explanations
- Adam: A Method for Stochastic Optimization
- Quantifying Attention Flow in Transformers
- Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers
- Quantum Self-Attention Neural Networks for Text Classification
- Quantum Mixed-State Self-Attention Network
- A Survey of Quantum Transformers: Architectures, Challenges and Outlooks
- Quixer: A Quantum Transformer Model
- Quantum Transformer: Accelerating model inference via quantum linear algebra
- A Quantum Roadmap for Softmax Attention: Exact Born-Rule Analogs for Softmax Attention on the Probability Simplex
- QLENS: Towards A Quantum Perspective of Language Transformers
- Watching Quantum Models Think: Hilbert-Space Interpretability in Quantum Transformer Blocks
Related papers
- Computational regimes in matrix-product-state-based quantum trajectory simulations
- Toward chemically accurate quantum simulations on quantum hardware: A quantum-HPC hybrid approach
- Transversal surface-code game with reconfigurable qubits
- Fulqrum: a generalized framework for quantum subspace diagonalization
- Flux-Activated Resonant Control of a Bosonic Quantum Memory
- Machine learning the effects of many quantum measurements