Abstract

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. Inspired by recent work on the practice of encoding human-interpretable concepts linearly within large language models, we treat truthfulness as a specially linearly encoded concept within LLMs, and introduce Adaptive Activation Steering (ACT), a tuning-free method that adaptively shifts LLM’s activations in the “truthful” direction during inference. ACT addresses diverse categories of hallucinations by utilizing diverse truthfulness-related steering vectors and adjusting the steering intensity adaptively. Applied as an add-on across various models, ACT significantly improves truthfulness in LLaMA (142%), LLaMA2 (24%), Alpaca (36%), Vicuna (28%), LLaMA2-Chat (19%), and LLaMA3(34%). Furthermore, we verify ACT’s scalability across larger models (13B, 33B, 65B), underscoring the adaptability of ACT to large-scale language models. Code: https://anonymous.4open.science/r/ACT24.