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

TL;DR

The paper introduces Adaptive Activation Steering (ACT), a tuning-free method that enhances the truthfulness of large language models by adaptively shifting their activations during inference, effectively reducing hallucinations across various models and scales.

Contribution

We propose ACT, a novel tuning-free activation steering technique that encodes truthfulness as a linear concept and adaptively adjusts model activations to improve factual accuracy.

Findings

Significantly improves truthfulness in multiple LLMs (up to 142%).

Demonstrates scalability across models from 13B to 65B parameters.

Effective across diverse hallucination categories.

Abstract

Recent studies have indicated that Large Language Models (LLMs) harbor an inherent understanding of truthfulness, yet often fail to consistently express it 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 ($\uparrow$ 142%), LLaMA2 ($\uparrow$ 24%), Alpaca ($\uparrow$ 36%), Vicuna ($\uparrow$ 28%), LLaMA2-Chat ($\uparrow$ 19%), and LLaMA3($\uparrow$ 34%). Furthermore, we verify ACT's scalability across larger models (13B, 33B, 65B), underscoring the adaptability of ACT to large-scale language models. Our code is available at https://github.com/tianlwang/ACT.