2 papers
cs.CL2026
Claim-Level Confidence Calibration for Reliable Decision Making with Large Language Models
Toghrul Abbasli, Kentaroh Toyoda, Yuan Wang +1
Large Language Models (LLMs) increasingly support decision-making in high-stakes domains, but they often hallucinate and express confidence that is misaligned with factual correctn…
quant-ph2025
Quasi-Orthogonality and Polysemy: The Limits of Quantum Analogy in Large Language Models
Karl Svozil
We analyze two geometric aspects of meaning-sensitive behavior in next-token models. First, high-dimensional geometry permits exponentially many nearly orthogonal feature direction…