Table 7: Examples of Generated Cartoon Descriptions Type of descriptions GPT -4o Human Written [20] Canny description A knight in armor is riding a horse, holding a lance with a traffic light on top. A line of businessmen in suits follows behind him. There are two men on a horse. They are wearing soldier outfits. Uncanny Description It's unusual to see a medieval knight leading modern businessmen as if going into battle.

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.

Table 7: Examples of Generated Cartoon Descriptions Type of descriptions GPT -4o Human Written [20] Canny description A knight in armor is riding a horse, holding a lance with a traffic light on top. A line of businessmen in suits follows behind him. There are two men on a horse. They are wearing soldier outfits. Uncanny Description It's unusual to see a medieval knight leading modern businessmen as if going into battle.

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.

We present a novel multimodal preference dataset for creative tasks, consisting of over 250 million human ratings 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.

In this article, I'll show you how I built a system called AI-Memer that generates memes using the latest AI models. I start with a high-level description of the system components before getting into the background of memes and details of the components. I'll then show you how to generate your own memes using the Google Colab, here. After a brief discussion of results and next steps, you can see some sample memes in the appendix. Oh, and I'll show a newly generated meme at the head of each section.