# Witscript 3: A Hybrid AI System for Improvising Jokes in a Conversation

arXiv: https://arxiv.org/abs/2301.02695 · HTML: https://mlsanity.com/paper/2301.02695/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 25 references that are in the map.
- First posted on arXiv 6 Jan 2023.

## Builds on (most cited first, 4 of 4)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts](https://mlsanity.com/paper/2110.01691/) (2021)
- [Reverse-Engineering Satire, or "Paper on Computational Humor Accepted Despite Making Serious Advances"](https://mlsanity.com/paper/1901.03253/) (2019)
- [Let's be Humorous: Knowledge Enhanced Humor Generation](https://mlsanity.com/paper/2004.13317/) (2020)

## Built on by (most cited first, 8 of 8)

- [A Robot Walks into a Bar: Can Language Models Serve as Creativity Support Tools for Comedy? An Evaluation of LLMs' Humour Alignment with Comedians](https://mlsanity.com/paper/2405.20956/) (2024)
- ["A good pun is its own reword": Can Large Language Models Understand Puns?](https://mlsanity.com/paper/2404.13599/) (2024)
- [Recent Advancement of Emotion Cognition in Large Language Models](https://mlsanity.com/paper/2409.13354/) (2024)
- [Humor Mechanics: Advancing Humor Generation with Multistep Reasoning](https://mlsanity.com/paper/2405.07280/) (2024)
- [Prompt to GPT-3: Step-by-Step Thinking Instructions for Humor Generation](https://mlsanity.com/paper/2306.13195/) (2023)
- [The Theater Stage as Laboratory: Review of Real-Time Comedy LLM Systems for Live Performance](https://mlsanity.com/paper/2501.08474/) (2025)
- [THInC: A Theory-Driven Framework for Computational Humor Detection](https://mlsanity.com/paper/2409.01232/) (2024)
- ["Not Human, Funnier": How Machine Identity Shapes Humor Perception in Online AI Stand-up Comedy](https://mlsanity.com/paper/2602.12763/) (2026)

## Abstract (arXiv)

Previous papers presented Witscript and Witscript 2, AI systems for improvising jokes in a conversation. Witscript generates jokes that rely on wordplay, whereas the jokes generated by Witscript 2 rely on common sense. This paper extends that earlier work by presenting Witscript 3, which generates joke candidates using three joke production mechanisms and then selects the best candidate to output. Like Witscript and Witscript 2, Witscript 3 is based on humor algorithms created by an expert comedy writer. Human evaluators judged Witscript 3's responses to input sentences to be jokes 44% of the time. This is evidence that Witscript 3 represents another step toward giving a chatbot a humanlike sense of humor.