对话：喜欢它们，讨厌它们，引导它们
Conversations: Love Them, Hate Them, Steer Them
AI总结：
本文通过激活工程引导LLaMA 3.1-8B增强情感表达，提升对话AI的共情能力。
摘要：
大型语言模型（LLMs）表现出日益增强的对话流畅性，但赋予它们细腻、人性化的情感表达仍是一个重大挑战。当前的对齐技术往往只解决表层输出或需要大量微调。本文证明，通过有针对性的激活工程可以引导LLaMA 3.1-8B表现出更人性化的情感细微差别。我们首先采用归因修补法来识别因果影响的组件，在诊断对话任务中通过观察激活模式来找到关键干预点。然后从对比文本对（正例与负例）生成的激活差异中推导出情感表达向量。将这些向量应用于新的对话提示显著增强了情感特征：引导响应显示出更高的积极情绪（例如，喜悦、信任）以及更频繁的第一人称代词使用，表明更大的个人参与。我们的发现提供了一种精确且可解释的方法，用于控制LLMs中的特定情感属性，有助于开发更加对齐和共情的对话AI。
英文摘要：
Large Language Models (LLMs) demonstrate increasing conversational fluency, yet instilling them with nuanced, human-like emotional expression remains a significant challenge. Current alignment techniques often address surface-level output or require extensive fine-tuning. This paper demonstrates that targeted activation engineering can steer LLaMA 3.1-8B to exhibit more human-like emotional nuances. We first employ attribution patching to identify causally influential components, to find a key intervention locus by observing activation patterns during diagnostic conversational tasks. We then derive emotional expression vectors from the difference in the activations generated by contrastive text pairs (positive vs. negative examples of target emotions). Applying these vectors to new conversational prompts significantly enhances emotional characteristics: steered responses show increased positive sentiment (e.g., joy, trust) and more frequent first-person pronoun usage, indicative of greater personal engagement. Our findings offer a precise and interpretable method for controlling specific emotional attributes in LLMs, contributing to developing more aligned and empathetic conversational AI.
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。
