2000 character limit reached
Humor Mechanics: Advancing Humor Generation with Multistep Reasoning (2405.07280v1)
Published 12 May 2024 in cs.CL, cs.AI, cs.CY, and cs.HC
Abstract: In this paper, we explore the generation of one-liner jokes through multi-step reasoning. Our work involved reconstructing the process behind creating humorous one-liners and developing a working prototype for humor generation. We conducted comprehensive experiments with human participants to evaluate our approach, comparing it with human-created jokes, zero-shot GPT-4 generated humor, and other baselines. The evaluation focused on the quality of humor produced, using human labeling as a benchmark. Our findings demonstrate that the multi-step reasoning approach consistently improves the quality of generated humor. We present the results and share the datasets used in our experiments, offering insights into enhancing humor generation with artificial intelligence.
- Aaronson, S. 2009. Essentials of complexity-theoretic stand-up comedy. https://scottaaronson.blog/?p=414.
- 2020. Paranoid transformer: Reading narrative of madness as computational approach to creativity. Future Internet 12(11).
- 2016. The neural correlates of humor creativity. Front. Hum. Neurosci. 10:597.
- 2023. A theory for emergence of complex skills in language models. https://arxiv.org/abs/2307.15936.
- Attardo, S. 1994. Linguistic Theories of Humor. Berlin, New York: De Gruyter Mouton.
- 2023. You told me that joke twice: A systematic investigation of transferability and robustness of humor detection models. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing 13701–13715.
- 2021. On the dangers of stochastic parrots: Can language models be too big? Proceedings of the 2021 ACM conference on fairness, accountability, and transparency 610–623.
- 2023. Prompt to gpt-3: Step-by-step thinking instructions for humor generation. 14th International Conference on Computational Creativity.
- 2020. The winograd schemas from hell. In Proceedings of the 17th National Meeting on Artificial and Computational Intelligence, 531–542. Porto Alegre, RS, Brasil: SBC.
- 2022. The idea machine: Llm-based expansion, rewriting, combination, and suggestion of ideas. Proceedings of the 14th Conference on Creativity and Cognition 623–627.
- 2023. Do androids laugh at electric sheep? humor ”understanding” benchmarks from the new yorker caption contest.
- 2023. A conversation about ai risk. https://twitter.com/AndrewYNg/status/1667920020587020290?lang=en.
- 2020. Compositionality decomposed: how do neural networks generalise? Journal of Artificial Intelligence Research 67:757–795.
- 2011. Inside Jokes: Using Humor to Reverse-Engineer the Mind. The MIT Press.
- 2023. What do humor classifiers learn? an attempt to explain humor recognition models. In Degaetano-Ortlieb, S.; Kazantseva, A.; Reiter, N.; and Szpakowicz, S., eds., Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, 88–98. Dubrovnik, Croatia: Association for Computational Linguistics.
- 2023. Chatgpt is fun, but it is not funny! humor is still challenging large language models. Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, and Social Media Analysis 325–340.
- Koestler, A. 1964. The Act of Creation: A Study of Conscious and Unconscious Processes of Humor, Scientific Discovery and Art.
- 2023. The iron(ic) melting pot: Reviewing human evaluation in humour, irony and sarcasm generation. Findings of the Association for Computational Linguistics: EMNLP 2023 6676–6689.
- 1947. On a Test of Whether one of Two Random Variables is Stochastically Larger than the Other. The Annals of Mathematical Statistics 18(1):50–60.
- 2023. The quantization model of neural scaling. 37th Conference on Neural Information Processing Systems.
- Mihalcea, and Strapparava. 2005. Making computers laugh: Investigations in automatic humor recognition. Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing 531–538.
- 2017. Humor, laughter, learning, and health! a brief review. Advances in physiology education. 341––347.
- 2000. Resolving conflict with humor in a diversity context. Journal of Managerial Psychology Vol. 15 No. 6:606––625.
- 2023. Brainstorm, then select: a generative language model improves its creativity score.
- 2022. Expunations: Augmenting puns with keywords and explanations. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing 4590–4605.
- Szegedy, C. 2024. https://twitter.com/ChrSzegedy/status/1750196565409701979.
- 2023. Post Turing: Mapping the landscape of LLM evaluation. In Gehrmann, S.; Wang, A.; Sedoc, J.; Clark, E.; Dhole, K.; Chandu, K. R.; Santus, E.; and Sedghamiz, H., eds., Proceedings of the Third Workshop on Natural Language Generation, Evaluation, and Metrics (GEM), 398–412. Singapore: Association for Computational Linguistics.
- Toplyn, J. 2014. Comedy Writing for Late-Night TV: How to Write Monologue Jokes, Desk Pieces, Sketches, Parodies, Audience Pieces, Remotes, and Other Short-Form Comedy.
- Toplyn, J. 2021. Witscript: A system for generating improvised jokes in a conversation. In Proceedings of the 12th International Conference on Computational Creativity (ICCC ’21).
- Toplyn, J. 2022. Witscript 2: A system for generating improvised jokes without wordplay. In Proceedings of the 13th International Conference on Computational Creativity (ICCC ’22).
- Toplyn, J. 2023. Witscript 3: A hybrid ai system for improvising jokes in a conversation. https://arxiv.org/abs/2301.02695.
- Veale, T. 2001. Your Wit Is My Command: Building AIs with a Sense of Humor. The MIT Press.
- 2024. Can ai be as creative as humans? https://arxiv.org/abs/2401.01623.
- 2021. What makes things funny? an integrative review of the antecedents of laughter and amusement. Personality and Social Psychology Review Vol. 25(1):41–65.
- 2019. Humor detection: A transformer gets the last laugh. Proceedings of the 2019 Conference on Empirical Methods in Natu- ral Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) 3621–3625.
- 2023. Skill-mix: a flexible and expandable family of evaluations for ai models. https://arxiv.org/abs/2310.17567.