PclGPT: A Large Language Model for Patronizing and Condescending Language Detection

TL;DR

This paper introduces PclGPT, a large language model benchmark specifically designed to detect patronizing and condescending language, addressing the limitations of traditional models in identifying implicit toxicity.

Contribution

The paper develops PclGPT, a novel bilingual LLM benchmark with a specialized dataset and training process for implicit toxic language detection, highlighting biases across vulnerable groups.

Findings

PclGPT outperforms traditional models in detecting PCL.

Significant bias variations in PCL towards different groups.

Enhanced societal awareness of implicit toxicity issues.

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.