# Grounded Satirical Generation with RAG

arXiv: https://arxiv.org/abs/2605.10853 · HTML: https://mlsanity.com/paper/2605.10853/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 30 references that are in the map.
- First posted on arXiv 11 May 2026.

## Builds on (most cited first, 10 of 10)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [EuroLLM: Multilingual Language Models for Europe](https://mlsanity.com/paper/2409.16235/) (2024)
- [Human Evaluation of Creative NLG Systems: An Interdisciplinary Survey on Recent Papers](https://mlsanity.com/paper/2108.00308/) (2021)
- [We Are Humor Beings: Understanding and Predicting Visual Humor](https://mlsanity.com/paper/1512.04407/) (2015)
- [Getting Serious about Humor: Crafting Humor Datasets with Unfunny Large Language Models](https://mlsanity.com/paper/2403.00794/) (2024)
- [BottleHumor: Self-Informed Humor Explanation using the Information Bottleneck Principle](https://mlsanity.com/paper/2502.18331/) (2025)
- [Augmenting emotion features in irony detection with Large language modeling](https://mlsanity.com/paper/2404.12291/) (2024)
- [Make Satire Boring Again: Reducing Stylistic Bias of Satirical Corpus by Utilizing Generative LLMs](https://mlsanity.com/paper/2412.09247/) (2024)

## Abstract (arXiv)

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.