I’m sure you’re a real scholar yourself: Exploring Ironic Content Generation by Large Language Models

Pier 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.
Anthology ID:
2024.findings-emnlp.847
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14480–14494
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.847
DOI:
Bibkey:
Cite (ACL):
Pier Balestrucci, Silvia Casola, Soda Marem Lo, Valerio Basile, and Alessandro Mazzei. 2024. I’m sure you’re a real scholar yourself: Exploring Ironic Content Generation by Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 14480–14494, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
I’m sure you’re a real scholar yourself: Exploring Ironic Content Generation by Large Language Models (Balestrucci et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.847.pdf
Data:
 2024.findings-emnlp.847.data.zip