Robust Explanations for User Trust in Enterprise NLP Systems
A new preprint introduces a unified black-box robustness evaluation framework for token-level explanations in enterprise NLP systems. The study systematically compares encoder and decoder models, finding that decoder LLMs yield significantly more stable explanations (73% lower flip rates on average) and that explanation stability increases with model scale (44% improvement from 7B to 70B parameters). The work also presents a practical cost-robustness tradeoff curve to inform model selection before deployment in compliance-sensitive environments.
Why it matters: This framework addresses a key challenge in validating explanation robustness for black-box NLP systems, supporting user trust and regulatory compliance in enterprise applications.
Full story at: arXiv Computation and Language ↗