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

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 prac...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Yu, Jiang, Han, Gong, Chuanyang, Wei, Zhihua
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
DOI:10.48550/arxiv.2404.10464