Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning
Jifan Zhang, Lalit K Jain, Yang Guo, Jiayi Chen, Kuan Lok Zhou, Siddharth Suresh, Andrew Wagenmaker, Scott Sievert
Abstract
We present a novel multimodal preference dataset for creative tasks, consisting of over 250 million human votes on more than 2.2 million captions, collected through crowdsourcing rating data for The New Yorker's weekly cartoon caption contest over the past eight years. This unique dataset supports the development and evaluation of multimodal large language models and preference-based fine-tuning algorithms for humorous caption generation. We propose novel benchmarks for judging the quality of model-generated captions, utilizing both GPT4 and human judgments to establish ranking-based evaluation strategies. Our experimental results highlight the limitations of current fine-tuning methods, such as RLHF and DPO, when applied to creative tasks. Furthermore, we demonstrate that even state-of-the-art models like GPT4 and Claude currently underperform top human contestants in generating humorous captions. As we conclude this extensive data collection effort, we release the entire preference dataset to the research community, fostering further advancements in AI humor generation and evaluation.
BibTeX
@inproceedings{
zhang2024humor,
title={Humor in {AI}: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning},
author={Jifan Zhang and Lalit K Jain and Yang Guo and Jiayi Chen and Kuan Lok Zhou and Siddharth Suresh and Andrew Wagenmaker and Scott Sievert and Timothy T. Rogers and Kevin Jamieson and Bob Mankoff and Robert D Nowak},
booktitle={The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
year={2024},
url={https://openreview.net/forum?id=w90ZH5v34S}
}