Attribute-Based Activation Steering of LLMs for Group-Specific Explanation Generation

Abstract:To effectively enable people to understand new topics, explanations should be tailored to their backgrounds and abilities. So far, prompting alone has been shown to be insufficient for creating such explanations and other computational methods are missing. Therefore, this paper investigates whether LLMs can be steered to generate explanations that are tailored to a specific group of people. To this end, we propose an approach that first identifies group-specific attributes in terms of explanatory style and knowledge of a specific target group. Building on activation engineering, it then computes attribute-based steering vectors and adds them to the internal activations of an LLM during inference to enable a fine-grained steering. In our experiments, we assess the steering effectiveness of our approach in terms of specificity and factuality of the generated explanations. Additionally, we evaluate the explanations in a study with human experts from different target groups. Compared to prompting and state-of-the-art steering baselines, our approach tailors the explanations significantly better to the target group while largely maintaining factuality.

Computation and Language (cs.CL)

arXiv:2608.29215 [cs.CL]

(or arXiv:2608.29215v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2608.29215 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.