Utsav Arora


2026

This paper describes the BAHAHA system for SemEval-2026 Task 1: MWAHAHA, which requires generating original jokes given either a news headline or a pair of rare words. Our approach uses a generate-then-rank pipeline, combining multi-style candidate generation via comedian-inspired few-shot prompting. We perform quality assessment from a smaller model fine-tuned on synthetic rating data from the generation model. Specifically, we produce up to 50 candidates per input across 15 stylistic templates and select outputs through a mixed-initiative interface that combines automated ranking with human judgment. There were 305 participants and 180 submissions in the contest. Our system ranks 2nd on Subtask A Chinese and 5th on Subtasks B1 and B2. The system generates jokes natively in each language rather than through translation.