机器人会被《纽约客》漫画逗笑吗？基于《纽约客》漫画配文竞赛的幽默“理解”基准
Do Androids Laugh at Electric Sheep? Humor "Understanding" Benchmarks from The New Yorker Caption Contest
AI总结：
该研究通过《纽约客》漫画配文竞赛构建三项幽默理解任务，发现多模态与纯语言模型均远逊于人类，并发布了相关模型、代码、排行榜及带标注的语料库。
摘要：
大型神经网络如今已经能够生成笑话，但它们真的“理解”幽默吗？我们利用源自《纽约客》漫画配文竞赛的三项任务来挑战AI模型：将笑话与漫画进行匹配、识别获胜配文，以及解释获胜配文为何好笑。这些任务逐步涵盖了“理解”一幅漫画所需的越来越复杂的方面；关键要素在于图像与配文之间复杂且常常出人意料的关系，以及对人类经验与文化中那些间接而俏皮的典故的频繁引用。我们同时考察了多模态模型和纯语言模型：前者直接面对漫画图像进行挑战，而后者则获得对视觉场景的多方面描述，以模拟人类水平的视觉理解。我们发现两类模型在这三项任务上均表现不佳。例如，我们最好的多模态模型在匹配任务上比人类表现落后30个准确率百分点；而且，即使提供了真实的视觉场景描述符，在超过三分之二的情况下，人类撰写的解释在直接对比中仍优于最好的机器撰写的解释（少样本GPT-4）。我们发布了模型、代码、排行榜和语料库，其中包含新收集的标注，用于描述图像中的地点/实体、场景中的不寻常之处以及对笑话的解释。
英文摘要：
Large neural networks can now generate jokes, but do they really "understand" humor? We challenge AI models with three tasks derived from the New Yorker Cartoon Caption Contest: matching a joke to a cartoon, identifying a winning caption, and explaining why a winning caption is funny. These tasks encapsulate progressively more sophisticated aspects of "understanding" a cartoon; key elements are the complex, often surprising relationships between images and captions and the frequent inclusion of indirect and playful allusions to human experience and culture. We investigate both multimodal and language-only models: the former are challenged with the cartoon images directly, while the latter are given multifaceted descriptions of the visual scene to simulate human-level visual understanding. We find that both types of models struggle at all three tasks. For example, our best multimodal models fall 30 accuracy points behind human performance on the matching task, and, even when provided ground-truth visual scene descriptors, human-authored explanations are preferred head-to-head over the best machine-authored ones (few-shot GPT-4) in more than 2/3 of cases. We release models, code, leaderboard, and corpus, which includes newly-gathered annotations describing the image's locations/entities, what's unusual in the scene, and an explanation of the joke.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
