Tears or Cheers? Benchmarking LLMs via Culturally Elicited Distinct Affective Responses

Culture serves as a fundamental determinant of human affective processing and profoundly shapes how individuals perceive and interpret emotional stimuli. Despite this intrinsic link extant evaluations regarding cultural alignment within Large Language Models primarily prioritize declarative knowledge such as geographical facts or established societal customs. These benchmarks remain insufficient to capture the subjective interpretative variance inherent to diverse sociocultural lenses. To address this limitation, we introduce CEDAR, a multimodal benchmark constructed entirely from scenarios capturing Culturally Elicited Distinct Affective Responses. To construct CEDAR, we implement a novel pipeline that leverages LLMgenerated provisional labels to isolate instances yielding cross-cultural emotional distinctions, and subsequently derives reliable ground-truth annotations through rigorous human evaluation. The resulting benchmark comprises 10,962 instances across seven languages and 14 finegrained emotion categories, with each language including 400 multimodal and 1,166 text-only samples. Comprehensive evaluations of 17 representative multilingual models reveal a dissociation between language consistency and cultural alignment, demonstrating that culturally grounded affective understanding remains a significant challenge for current models. Codes and datasets will be released soon 1 . * Equal contribution 1 https://github.com/MindIntLab-HFUT/CEDAR ar How does the person standing near the lanterns feel during this moment? MULTIMODAL Guests fill the room, knowing the event celebrates new beginnings. Before arrival, one guest wraps a gift in black paper. You hesitate, unsure how to react. How do you feel upon seeing the black-wrapped gift?