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

arXiv: https://arxiv.org/abs/2608.29215 · HTML: https://mlsanity.com/paper/2608.29215/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Activation steering methods, one of 13 directions in Mechanistic interpretability.
- Builds on 33 of its 62 references that are in the map.
- First posted on arXiv 29 Aug 2026.

## Placed in

- Mechanistic interpretability / [Activation steering methods](https://mlsanity.com/mechinterp/activation-steering-methods/)

## Builds on (most cited first, 30 of 33)

- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [ELI5: Long Form Question Answering](https://mlsanity.com/paper/1907.09190/) (2019)
- [KILT: a Benchmark for Knowledge Intensive Language Tasks](https://mlsanity.com/paper/2009.02252/) (2020)
- [Explaining Explanations: An Overview of Interpretability of Machine Learning](https://mlsanity.com/paper/1806.00069/) (2018)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Deep Learning for Text Style Transfer: A Survey](https://mlsanity.com/paper/2011.00416/) (2020)
- [Towards Faithful Model Explanation in NLP: A Survey](https://mlsanity.com/paper/2209.11326/) (2022)
- [Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations](https://mlsanity.com/paper/2210.11584/) (2022)
- [Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting](https://mlsanity.com/paper/2309.07034/) (2023)
- [Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories](https://mlsanity.com/paper/2406.00034/) (2024)
- [One Explanation Does Not Fit All: The Promise of Interactive Explanations for Machine Learning Transparency](https://mlsanity.com/paper/2001.09734/) (2020)
- [Exploring LLM Prompting Strategies for Joint Essay Scoring and Feedback Generation](https://mlsanity.com/paper/2404.15845/) (2024)
- [Style Vectors for Steering Generative Large Language Model](https://mlsanity.com/paper/2402.01618/) (2024)
- [Multi-Attribute Steering of Language Models via Targeted Intervention](https://mlsanity.com/paper/2502.12446/) (2025)
- [SemEval-2020 Task 4: Commonsense Validation and Explanation](https://mlsanity.com/paper/2007.00236/) (2020)
- [Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Models](https://mlsanity.com/paper/2310.05253/) (2023)
- [Learning Interpretable Style Embeddings via Prompting LLMs](https://mlsanity.com/paper/2305.12696/) (2023)
- [User Embedding Model for Personalized Language Prompting](https://mlsanity.com/paper/2401.04858/) (2024)
- [Beyond Linear Steering: Unified Multi-Attribute Control for Language Models](https://mlsanity.com/paper/2505.24535/) (2025)
- [Style-Specific Neurons for Steering LLMs in Text Style Transfer](https://mlsanity.com/paper/2410.00593/) (2024)
- [Know Your Audience: Do LLMs Adapt to Different Age and Education Levels?](https://mlsanity.com/paper/2312.02065/) (2023)
- [Belief-based Generation of Argumentative Claims](https://mlsanity.com/paper/2101.09765/) (2021)
- [Embedding-to-Prefix: Parameter-Efficient Personalization for Pre-Trained Large Language Models](https://mlsanity.com/paper/2505.17051/) (2025)
- [Towards Content Transfer through Grounded Text Generation](https://mlsanity.com/paper/1905.05293/) (2019)

## Abstract (arXiv)

To effectively enable people to understand new topics, explanations should be tailored to their backgrounds and abilities. Prompting alone has been shown to be insufficient for creating such explanations, and other computational methods are missing so far. 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 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 maintaining the best specificity-factuality balance.