paper-with-me

홈 › Papers

Language Model Detoxification in Dialogue with Contextualized Stance Control

2023-01-25 · Jing Qian, Xifeng Yan

To reduce the toxic degeneration in a pretrained Language Model (LM), previous work on Language Model detoxification has focused on reducing the toxicity of the generation itself (self-toxicity) without consideration of the context. As a result, a type of implicit offensive language where the generations support the offensive language in the context is ignored. Different from the LM controlling tasks in previous work, where the desired attributes are fixed for generation, the desired stance of the generation depends on the offensiveness of the context. Therefore, we propose a novel control method to do context-dependent detoxification with the stance taken into consideration. We introduce meta prefixes to learn the contextualized stance control strategy and to generate the stance control prefix according to the input context. The generated stance prefix is then combined with the toxicity control prefix to guide the response generation. Experimental results show that our proposed method can effectively learn the context-dependent stance control strategies while keeping a low self-toxicity of the underlying LM.

📄 PDF Abstract BibTeX arXiv:2301.10368

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingResponse Generation

Similar Papers 제목 키워드 기반

Fine-Grained Detoxification via Instance-Level Prefixes for Large Language Models

2024-02-23 · Xin Yi, LinLin Wang, Xiaoling Wang, Liang He

Impressive results have been achieved in natural language processing (NLP) tasks through the training of large language models (LLMs). However, these models occasionally produce toxic content such as insults, threats, an…

DiversityText Generation

Chinese Toxic Language Mitigation via Sentiment Polarity Consistent Rewrites

2025-05-21 · Xintong Wang, Yixiao Liu, Jingheng Pan, Liang Ding 외

Detoxifying offensive language while preserving the speaker's original intent is a challenging yet critical goal for improving the quality of online interactions. Although large language models (LLMs) show promise in rew…

Sentence

Language Detoxification with Attribute-Discriminative Latent Space

2022-10-19 · Jin Myung Kwak, Minseon Kim, Sung Ju Hwang

Transformer-based Language Models (LMs) have achieved impressive results on natural language understanding tasks, but they can also generate toxic text such as insults, threats, and profanity, limiting their real-world a…

AttributeDialogue GenerationLanguage ModelingLanguage Modelling+2

Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts

2022-12-20 · Skyler Hallinan, Alisa Liu, Yejin Choi, Maarten Sap

Text detoxification has the potential to mitigate the harms of toxicity by rephrasing text to remove offensive meaning, but subtle toxicity remains challenging to tackle. We introduce MaRCo, a detoxification algorithm th…

Methods for Detoxification of Texts for the Russian Language

2021-05-19 · Daryna Dementieva, Daniil Moskovskiy, Varvara Logacheva, David Dale 외

We introduce the first study of automatic detoxification of Russian texts to combat offensive language. Such a kind of textual style transfer can be used, for instance, for processing toxic content in social media. While…

Style Transfer