Make Satire Boring Again: Reducing Stylistic Bias of Satirical Corpus by Utilizing Generative LLMs
This addresses the problem of misinformation and opinion extraction for researchers and practitioners in NLP by providing a debiasing method and a new Turkish dataset, but it is incremental as it builds on existing LLM techniques.
The study tackled stylistic bias in satire detection by using generative LLMs to debias training data, resulting in enhanced robustness and generalizability for satire and irony detection in Turkish and English, though with limited impact on models like Llama-3.1.
Satire detection is essential for accurately extracting opinions from textual data and combating misinformation online. However, the lack of diverse corpora for satire leads to the problem of stylistic bias which impacts the models' detection performances. This study proposes a debiasing approach for satire detection, focusing on reducing biases in training data by utilizing generative large language models. The approach is evaluated in both cross-domain (irony detection) and cross-lingual (English) settings. Results show that the debiasing method enhances the robustness and generalizability of the models for satire and irony detection tasks in Turkish and English. However, its impact on causal language models, such as Llama-3.1, is limited. Additionally, this work curates and presents the Turkish Satirical News Dataset with detailed human annotations, with case studies on classification, debiasing, and explainability.