EMNLP Findings2024
I'm sure you're a real scholar yourself: Exploring Ironic Content Generation by Large Language Models
Pier Felice Balestrucci, Silvia Casola, Soda Marem Lo, Valerio Basile, Alessandro Mazzei
Abstract
Generating ironic content is challenging: it requires a nuanced understanding of context and implicit references and balancing seriousness and playfulness. Moreover, irony is highly subjective and can depend on various factors, such as social, cultural, or generational aspects. This paper explores whether Large Language Models (LLMs) can learn to generate ironic responses to social media posts. To do so, we fine-tune two models to generate ironic and non-ironic content and deeply analyze their outputs' linguistic characteristics, their connection to the original post, and their similarity to the human-written replies. We also conduct a large-scale human evaluation of the outputs. Additionally, we investigate whether LLMs can learn a form of irony tied to a generational perspective, with mixed results 1 .
Warning: Some examples shown in this paper contain offensive language, discriminatory remarks, and slurs.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers1
Builds on8
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- R^3: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense KnowledgeTuhin Chakrabarty, Debanjan Ghosh, Smaranda Muresan, Nanyun PengACL 2020 · 58 citations
- Should a Chatbot be Sarcastic? Understanding User Preferences Towards Sarcasm GenerationSilviu Vlad Oprea, Steven R. Wilson, Walid MagdyACL 2022 · 12 citations
- EPIC: Multi-Perspective Annotation of a Corpus of IronySimona Frenda, Alessandro Pedrani, Valerio Basile, Soda Marem Lo et al.ACL 2023 · 9 citations
- A Unified Framework for Pun Generation with Humor PrinciplesYufei Tian, Divyanshu Sheth, Nanyun PengEMNLP Findings 2022 · 8 citations
Related papers
- Decision Biases and Intent-Irony Decoupling in Large Language ModelsKewei Guo, Lingyun Sun, Manhao GuanACL Findings 2026
- "A good pun is its own reword": Can Large Language Models Understand Puns?Zhijun Xu, Siyu Yuan, Lingjie Chen, Deqing YangEMNLP 2024 · 6 citations
- MultiPICo: Multilingual Perspectivist Irony CorpusSilvia Casola, Simona Frenda, Soda Marem Lo, Erhan Sezerer et al.ACL 2024 · 2 citations
- Explicit vs. Implicit: Investigating Social Bias in Large Language Models through Self-ReflectionYachao Zhao, Bo Wang, Yan Wang, Dongming Zhao et al.ACL Findings 2025 · 4 citations
- FanChuan: A Multilingual and Graph-Structured Benchmark For Parody Detection and AnalysisYilun Zheng, Sha Li, Fangkun Wu, Yang Ziyi et al.ACL Findings 2025 · 1 citation
