lmfaoooo at SemEval-2026 Task 1: 幽默是受众。面向约束幽默生成的偏好建模
lmfaoooo at SemEval-2026 Task 1: Humor Is an Audience. Preference Modeling for Constrained Humor Generation
AI总结：
针对约束幽默生成任务，提出“生成多候选-偏好选择”策略，利用人类成对比较训练偏好模型，在MWAHAHA任务英、中、西语子任务中分别获得第1、第1和第2名。
摘要：
幽默生成仍然困难，不仅因为生成流畅、新颖的笑话很难，而且因为“有趣”取决于受众，监督信号嘈杂——偏好随受众、语境和文化而变化，标注者一致性通常较低。在本文中，我们描述了用于SemEval-2026 Task-1（MWAHAHA）的系统，该任务专注于在显式约束下进行幽默生成。任务通过1对1竞技场式比较中的人类偏好判断来评估提交的系统。我们采用“生成多个->选择最佳”策略。首先，我们通过多步提示、模型集成和多样性导向解码为每个实例生成多样化的候选池。其次，我们使用偏好模型选择输出，该模型通过从人类比较中学习（而非绝对趣味性分数）来近似“读者”。为支持该方法，我们发布了通过幽默竞技场原型收集的2.5K人类成对判断。我们进一步提出一个可解释的流程，将标注的比较转换为偏好模型。在三个偏好数据集上，我们的模型一致优于基线，并表现出更强的跨领域迁移。最后，我们将学到的偏好模型应用于MWAHAHA设置中的候选排序，并发布中间产物（候选池和排序）以促进后续工作。我们的系统在MWAHAHA的英语和汉语子任务中排名第一，在西班牙语子任务中排名第二。
英文摘要：
Humor generation remains difficult not only because producing fluent, novel jokes is hard, but because "funny" is audience-dependent and supervision is noisy -- preferences vary with audience, context, and culture, and annotator agreement is often low. In this paper, we describe our system for the SemEval-2026 Task-1 (MWAHAHA), which focuses on humor generation under explicit constraints. The task evaluates submitted systems via human preference judgments in 1-on-1 arena-style comparisons. We adopt a "generate-many -> select-best" strategy. First, we generate a diverse pool of candidates per instance using multi-step prompting, model ensembling, and diversity-oriented decoding. Second, we select outputs using a preference model that approximates a "reader" by learning from human comparisons rather than absolute funniness scores. To support this approach, we release 2.5K human pairwise judgments collected through the Humor Arena prototype. We further propose an interpretable pipeline that converts labeled comparisons into a preference model. Across three preference datasets, our models consistently outperform baselines and show stronger cross-domain transfer. Finally, we apply the learned preference model to rank candidates for the MWAHAHA setting and release intermediate artifacts (candidate pools and rankings) to facilitate follow-up work. Our system ranked 1st in the English and Chinese subtasks of MWAHAHA and 2nd in the Spanish subtask.
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。
