Policy Compliance of User Requests in Natural Language for AI Systems

TL;DR

This paper introduces a new benchmark for evaluating how well AI systems can assess whether user requests in natural language comply with organizational policies, highlighting the challenge of ensuring safe AI use.

Contribution

It presents the first benchmark dataset for policy compliance of user requests and evaluates various LLM models on this task, revealing performance challenges.

Findings

Benchmark dataset for policy compliance created and annotated.

LLM models show varying performance levels on compliance assessment.

The task is inherently challenging for current models.

Abstract

Consider an organization whose users send requests in natural language to an AI system that fulfills them by carrying out specific tasks. In this paper, we consider the problem of ensuring such user requests comply with a list of diverse policies determined by the organization with the purpose of guaranteeing the safe and reliable use of the AI system. We propose, to the best of our knowledge, the first benchmark consisting of annotated user requests of diverse compliance with respect to a list of policies. Our benchmark is related to industrial applications in the technology sector. We then use our benchmark to evaluate the performance of various LLM models on policy compliance assessment under different solution methods. We analyze the differences on performance metrics across the models and solution methods, showcasing the challenging nature of our problem.