Teacher Supervision, Fixed Representations and Calibration: Exact Risk Calculations for Candidate-Scoring Decision Models
Resumo indisponível. Consulte o paper original.
PAPER / ARXIV:2610.12718
David García-Lorite, Raul Merino
RESUMO
Large language models are stochastic by nature. Repeated executions under the same experimental conditions may produce different responses. We propose a framework that can be applied across the model lifecycle, from task design to residual behavior and continuous monitoring, built on an empirical response distribution estimated through Monte Carlo simulation. We illustrate the framework with two tasks, borrower classification and music album recommendation, and link it to model risk management and governance by measuring robustness and control effectiveness. Since it relies only on observed responses, it can also be applied to black-box models accessed through commercial APIs.
NO MESMO MAPA
Resumo indisponível. Consulte o paper original.
Resumo indisponível. Consulte o paper original.
Resumo indisponível. Consulte o paper original.