From Passive to Persuasive: Steering Emotional Nuance in Human-AI Negotiation
This addresses the problem of enhancing human-like emotional nuance in conversational AI for applications like negotiation, though it is incremental as it builds on existing activation engineering methods.
The paper tackled the challenge of instilling nuanced emotional expression in Large Language Models by using targeted activation engineering on LLaMA 3.1-8B, resulting in steered responses with increased positive sentiment and more frequent first-person pronoun usage.
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 framework and new directions for the study of conversational AI.