PclGPT: A Large Language Model for Patronizing and Condescending Language Detection
Hongbo Wang, LiMingDa LiMingDa, Junyu Lu, Hebin Xia, Liang Yang, Bo Xu, Ruizhu Liu, Hongfei Lin
Abstract
Disclaimer: Samples in this paper may be harmful and cause discomfort! Patronizing and condescending language (PCL) is a form of speech directed at vulnerable groups. As an essential branch of toxic language, this type of language exacerbates conflicts and confrontations among Internet communities and detrimentally impacts disadvantaged groups. Traditional pre-trained language models (PLMs) perform poorly in detecting PCL due to its implicit toxicity traits like hypocrisy and false sympathy. With the rise of large language models (LLMs), we can harness their rich emotional semantics to establish a paradigm for exploring implicit toxicity. In this paper, we introduce PclGPT, a comprehensive LLM benchmark designed specifically for PCL. We collect, annotate, and integrate the Pcl-PT/SFT dataset, and then develop a bilingual PclGPT-EN/CN model group through a comprehensive pre-training and supervised fine-tuning staircase process to facilitate implicit toxic detection. Group detection results and fine-grained detection from PclGPT and other models reveal significant variations in the degree of bias in PCL towards different vulnerable groups, necessitating increased societal attention to protect them.- Anthology ID:
- 2024.findings-emnlp.406
- Original:
- 2024.findings-emnlp.406v1
- Version 2:
- 2024.findings-emnlp.406v2
- 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:
- 6913–6928
- Language:
- URL:
- https://preview.aclanthology.org/icon-24-ingestion/2024.findings-emnlp.406/
- DOI:
- 10.18653/v1/2024.findings-emnlp.406
- Cite (ACL):
- Hongbo Wang, LiMingDa LiMingDa, Junyu Lu, Hebin Xia, Liang Yang, Bo Xu, Ruizhu Liu, and Hongfei Lin. 2024. PclGPT: A Large Language Model for Patronizing and Condescending Language Detection. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 6913–6928, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- PclGPT: A Large Language Model for Patronizing and Condescending Language Detection (Wang et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/icon-24-ingestion/2024.findings-emnlp.406.pdf