Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderation
This addresses the challenge of scalable human-AI collaboration for tasks such as social media moderation, offering a novel paradigm that is incremental in building on prior assistance-focused work.
The paper tackles the problem of effectively collaborating imperfect AI models with humans for scalable, low-stakes decisions like content moderation, proposing conditional delegation where humans create rules to indicate trustworthy model regions, and demonstrates improved model performance in experiments with in-distribution and out-of-distribution datasets.
Despite impressive performance in many benchmark datasets, AI models can still make mistakes, especially among out-of-distribution examples. It remains an open question how such imperfect models can be used effectively in collaboration with humans. Prior work has focused on AI assistance that helps people make individual high-stakes decisions, which is not scalable for a large amount of relatively low-stakes decisions, e.g., moderating social media comments. Instead, we propose conditional delegation as an alternative paradigm for human-AI collaboration where humans create rules to indicate trustworthy regions of a model. Using content moderation as a testbed, we develop novel interfaces to assist humans in creating conditional delegation rules and conduct a randomized experiment with two datasets to simulate in-distribution and out-of-distribution scenarios. Our study demonstrates the promise of conditional delegation in improving model performance and provides insights into design for this novel paradigm, including the effect of AI explanations.