Grounded Satirical Generation with RAG

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Itkonen, Oona, Su, Yuxin, Du, Linyao, De Gibert, Ona
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911671900962816
author Itkonen, Oona
Su, Yuxin
Du, Linyao
De Gibert, Ona
author_facet Itkonen, Oona
Su, Yuxin
Du, Linyao
De Gibert, Ona
contents Humor generation remains challenging task for Large Language Models (LLMs), due to their subjective nature. We focus on satire, a form of humor strongly shaped by context. In this work, we present a novel pipeline for grounded satire generation that uses Retrieval-Augmented Generation (RAG) over current news to produce satirical dictionary definitions in the Finnish context. We also introduce a new task-specific evaluation framework and annotate 100 generated definitions with six human annotators, enabling analysis across multiple experimental conditions, including cultural background, source-word type, and the presence or absence of RAG. Our results show that the generated definitions are perceived as more political than humorous. Both topic-based word selection and RAG improve the political relevance of the outputs, but neither yields clear gains in humor generation. In addition, our LLM-as-a-judge evaluation of five state-of-the-art models indicates that LLMs correlate well with human judgments on political relevance, but perform poorly on humor. We release our code and annotated dataset to support further research on grounded satire generation and evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2605_10853
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Grounded Satirical Generation with RAG
Itkonen, Oona
Su, Yuxin
Du, Linyao
De Gibert, Ona
Computation and Language
Humor generation remains challenging task for Large Language Models (LLMs), due to their subjective nature. We focus on satire, a form of humor strongly shaped by context. In this work, we present a novel pipeline for grounded satire generation that uses Retrieval-Augmented Generation (RAG) over current news to produce satirical dictionary definitions in the Finnish context. We also introduce a new task-specific evaluation framework and annotate 100 generated definitions with six human annotators, enabling analysis across multiple experimental conditions, including cultural background, source-word type, and the presence or absence of RAG. Our results show that the generated definitions are perceived as more political than humorous. Both topic-based word selection and RAG improve the political relevance of the outputs, but neither yields clear gains in humor generation. In addition, our LLM-as-a-judge evaluation of five state-of-the-art models indicates that LLMs correlate well with human judgments on political relevance, but perform poorly on humor. We release our code and annotated dataset to support further research on grounded satire generation and evaluation.
title Grounded Satirical Generation with RAG
topic Computation and Language
url https://arxiv.org/abs/2605.10853