标签
CUE-Bench is a Chinese benchmark for affective stance that models explicit-implicit polarity interaction and provides intent and fine-grained emotion annotations, showing gains in emotion recognition and pragmatic intent detection.
介绍了ConsumerSimBench，一个用于评估LLM从真实中文社交媒体话题中重建众包消费者反应能力的基准测试。测试表明，前沿模型仅覆盖了47.8%的真实反应标准，凸显了技术基准性能与社会直觉之间的差距。