ShieldHead: Decoding-time Safeguard for Large Language Models

ACL ARR 2025 February Submission1255 Authors

13 Feb 2025 (modified: 09 May 2025)ACL ARR 2025 February SubmissionEveryoneRevisionsBibTeXCC BY 4.0
Abstract:

In light of the widespread deployment of Large Language Models (LLMs), the responsibility for safeguarding and regulating LLM-generated content has taken on heightened significance. Recent advancements in LLM-based moderation methods, e.g., LlamaGuard, have demonstrated remarkable promise in identifying safety risks associated with both inputs and outputs in human-AI interactions. However, integrating LLM-based safeguards into a chatbot system requires an additional inference stage involving a moderation LLM with billions of parameters, which significantly increases computational costs and reduces overall efficiency. In this paper, we demonstrate that simply learning a classification head on the last-layer hidden states of the dialogue model provides a strong capability to identify harmful contents. The classification head, referred to as ShieldHead, serves as an auxiliary branch paralleled with next-token-prediction LM head, enabling the detection of potential risks in past text sequences. Additionally, a label disambiguation technique is employed to supervise ShieldHead with both token-level and sentence-level labels, which further enhances its performance. ShieldHead exhibits remarkable efficiency during inference, providing real-time moderation results alongside token-wise streaming output during the chatbot system's decoding phase. Extensive experimental results demonstrate the superiority of the proposed framework: a state-of-the-art performance on the XSTest and SafeRLHF datasets while running at a speed about 300× faster (<1ms) than previous LLM-based moderation models with ~99% less parameters of LlamaGuard.

Paper Type: Long
Research Area: Ethics, Bias, and Fairness
Research Area Keywords: Large Language Model, Safety Guard, Content Moderation
Contribution Types: Approaches low compute settings-efficiency
Languages Studied: English
Submission Number: 1255
Loading