自适应激活引导：一种面向多种幻觉类别的无需微调的大语言模型真实性提升方法
Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories
AI总结：
提出无需微调的自适应激活引导方法，通过调整LLM激活方向提升真实性，在多个模型上显著减少幻觉，并验证了其在大模型上的可扩展性。
摘要：
近期研究表明，大型语言模型（LLMs）对真实性有内在的理解，但往往无法始终如一地表达这种理解，从而产生虚假陈述。这种“知道”与“说出”之间的差距对确保生成内容的真实性构成了挑战。受近期关于在大语言模型中以线性方式编码人类可解释概念的研究启发，我们将真实性视为LLMs中一种特殊线性编码的概念，并引入了自适应激活引导（ACT），这是一种无需微调的方法，在推理过程中自适应地沿“真实”方向调整LLM的激活。ACT通过利用多种与真实性相关的引导向量并自适应地调整引导强度，来处理多种类别的幻觉。作为各种模型上的附加组件，ACT显著提高了LLaMA（上升142%）、LLaMA2（上升24%）、Alpaca（上升36%）、Vicuna（上升28%）、LLaMA2-Chat（上升19%）和LLaMA3（上升34%）的真实性。此外，我们验证了ACT在更大模型（13B、33B、65B）上的可扩展性，强调了ACT对大规模语言模型的适应性。我们的代码可在https://github.com/tianlwang/ACT获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
