DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation Fusion

16 Apr 2024  ·  Yu Li, Han Jiang, Chuanyang Gong, Zhihua Wei ·

Despite the remarkable achievements of language models (LMs) across a broad spectrum of tasks, their propensity for generating toxic outputs remains a prevalent concern. Current solutions involving finetuning or auxiliary models usually require extensive computational resources, hindering their practicality in large language models (LLMs). In this paper, we propose DeStein, a novel method that detoxifies LMs by applying representation engineering in activation spaces with lower resource and time costs. Specifically, we derive detoxification vectors from self-induced, universal steering pairs through arithmetic operations in activation spaces. During inference, detoxification is achieved by fusing the detoxification vectors with the original representations in a head-wise manner. Empirical results demonstrate that our method significantly outperforms previous state-of-the-art approaches on various metrics, while also maintaining satisfactory generation quality and diversity. We further validate the practicality and scalability of DeStein with a series of white-box LLMs. The method is open-sourced at https://github.com/LizLizLi/DeStein. Warning: Some example model outputs may contain highly offensive or disturbing text.

PDF Abstract

Datasets


Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here