Paper ID: 2406.00034

Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories

Tianlong Wang, Xianfeng Jiao, Yifan He, Zhongzhi Chen, Yinghao Zhu, Xu Chu, Junyi Gao, Yasha Wang, Liantao Ma

Recent studies have indicated that Large Language Models (LLMs) harbor an inherent understanding of truthfulness, yet often fail to express fully and generate false statements. This gap between "knowing" and "telling" poses a challenge for ensuring the truthfulness of generated content. To address this, we introduce Adaptive Activation Steering (ACT), a tuning-free method that adaptively shift LLM's activations in "truthful" direction during inference. ACT addresses diverse categories of hallucinations by utilizing diverse steering vectors and adjusting the steering intensity adaptively. Applied as an add-on across various models, ACT significantly improves truthfulness in LLaMA ($\uparrow$ 142\%), LLaMA2 ($\uparrow$ 24\%), Alpaca ($\uparrow$ 36\%), Vicuna ($\uparrow$ 28\%), and LLaMA2-Chat ($\uparrow$ 19\%). Furthermore, we verify ACT's scalability across larger models (13B, 33B, 65B), underscoring the adaptability of ACT to large-scale language models.

Submitted: May 26, 2024