You Really Didn't Get That? Benchmarking Social Pragmatic Inference for Indirect and Playful

We introduce a benchmark for evaluating whether LLMs can recover such situated pragmatic meanings. It comes from a paper posted to arXiv on 7 September 2026. Chinese online comments often convey social meaning through indirect and playful language that is hard to interpret without context. Existing evaluations largely organize items around predefined phenomena or controlled pragmatic categories, leaving open whether models can distinguish plausible readings of what a naturally occurring comment is doing in a particular exchange. From more than 200,000 public Chinese social media interaction records, we construct 4,735 human-validated diagnostic items, each pairing a target comment with reconstructed preceding context and plausible misreadings. We evaluate eight LLMs as both question writers and solvers in a cross-writer setting. The task is challenging: the strongest model achieves 81.42% leave-writer-out accuracy. Across all eight models, the mean leave-writer-out accuracy is 68.70% while human accuracy was 90.8%. Case analysis shows that models often recognize broad irony or playfulness while misidentifying the mechanism or interactional move.

Why it counts

We introduce a benchmark for evaluating whether LLMs can recover such situated pragmatic meanings.

Sources

Primary source: primary source

What is not known

This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.