# Language Model Detoxification in Dialogue with Contextualized Stance Control

arXiv: https://arxiv.org/abs/2301.10368 · HTML: https://mlsanity.com/paper/2301.10368/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 23 references that are in the map.
- First posted on arXiv 25 Jan 2023.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Universal Adversarial Triggers for Attacking and Analyzing NLP](https://mlsanity.com/paper/1908.07125/) (2019)
- [GeDi: Generative Discriminator Guided Sequence Generation](https://mlsanity.com/paper/2009.06367/) (2020)
- [SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020)](https://mlsanity.com/paper/2006.07235/) (2020)
- [Contextualizing Hate Speech Classifiers with Post-hoc Explanation](https://mlsanity.com/paper/2005.02439/) (2020)
- [Controllable Natural Language Generation with Contrastive Prefixes](https://mlsanity.com/paper/2202.13257/) (2022)
- [Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts](https://mlsanity.com/paper/2108.11830/) (2021)
- [Galileo at SemEval-2020 Task 12: Multi-lingual Learning for Offensive Language Identification using Pre-trained Language Models](https://mlsanity.com/paper/2010.03542/) (2020)

## Built on by (most cited first, 1 of 1)

- [Bot or Human? Detecting ChatGPT Imposters with A Single Question](https://mlsanity.com/paper/2305.06424/) (2023)

## Abstract (arXiv)

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.