Showing cs.CLShow all
2 papers · 1 filter
cs.CL2024
Learning from Relevant Subgoals in Successful Dialogs using Iterative Training for Task-oriented Dialog Systems
Magdalena Kaiser, Patrick Ernst, György Szarvas
Task-oriented Dialog (ToD) systems have to solve multiple subgoals to accomplish user goals, whereas feedback is often obtained only at the end of the dialog. In this work, we prop…
cs.CL2024
Calibrating Verbalized Probabilities for Large Language Models
Cheng Wang, Gyuri Szarvas, Georges Balazs +2
Calibrating verbalized probabilities presents a novel approach for reliably assessing and leveraging outputs from black-box Large Language Models (LLMs). Recent methods have demons…