Interpreting Reasoning of Large Language Models via Partial Information Decomposition
cs.IT, cs.AI, cs.CY, cs.LG, math.IT
Submitted: 2026-09-30
Updated: 2026-09-30
Related papers
- Language Modeling is Monotone Compression
- Clipped Affine Policy: Low-Complexity Near-Optimal Online Power Control for Energy Harvesting Communications over Fading Channels
- Discrepancy for Random Linear Codes
- A New Approach to Code Smoothing Bounds
- Contextual Memory-Enhanced Source Coding for Low-SNR Communications
- Symmetry-Enforced Quadratic Approximate-Degradability Bounds for Noisy Landau-Streater Channels