AI reasoning effort mirrors human decision time on content moderation tasks
This provides insights into AI interpretability and decision-making for content moderation applications, though it is incremental in nature.
The study found that AI reasoning effort predicts human decision time on content moderation tasks, with both showing increased effort when important variables were constant, indicating similar sensitivity to task difficulty.
Large language models can now generate intermediate reasoning steps before producing answers, improving performance on difficult problems. This study uses a paired conjoint experiment on a content moderation task to examine parallels between human decision times and model reasoning effort. Across three frontier models, reasoning effort consistently predicts human decision time. Both humans and models expended greater effort when important variables were held constant, suggesting similar sensitivity to task difficulty and patterns consistent with dual-process theories of cognition. These findings show that AI reasoning effort mirrors human processing time in subjective judgments and underscores the potential of reasoning traces for interpretability and decision-making.