works on
explainable AI 1feature attribution 1gradient methods 1perturbation analysis 1reporting standards 1shapley values 1

From the 1 of 2 linked papers with an AI index.

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

When Generic Prompt Improvements Hurt: Evaluation-Driven Iteration for LLM Applications

Daniel Commey

Evaluating Large Language Model (LLM) applications differs from conventional software testing because outputs are probabilistic, semantically variable, and sensitive to prompt and…