# Steerable Chatbots: Exploring Personalization Control Interfaces via LLM Activation Steering

arXiv: https://arxiv.org/abs/2505.04260 · HTML: https://mlsanity.com/paper/2505.04260/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Activation steering methods, one of 13 directions in Mechanistic interpretability.
- Builds on 47 of its 99 references that are in the map.
- First posted on arXiv 7 May 2025.

## Placed in

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

## Builds on (most cited first, 30 of 47)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://mlsanity.com/paper/2304.07327/) (2023)
- [TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification](https://mlsanity.com/paper/2010.12421/) (2020)
- [Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging](https://mlsanity.com/paper/2310.11564/) (2023)
- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards](https://mlsanity.com/paper/2306.04488/) (2023)
- [Extracting Latent Steering Vectors from Pretrained Language Models](https://mlsanity.com/paper/2205.05124/) (2022)
- [AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders](https://mlsanity.com/paper/2501.17148/) (2025)
- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [Programming Refusal with Conditional Activation Steering](https://mlsanity.com/paper/2409.05907/) (2024)
- [Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild](https://mlsanity.com/paper/1906.02569/) (2019)
- [Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment](https://mlsanity.com/paper/2402.10207/) (2024)
- [Improving Instruction-Following in Language Models through Activation Steering](https://mlsanity.com/paper/2410.12877/) (2024)
- [Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning](https://mlsanity.com/paper/2408.10075/) (2024)
- [Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization](https://mlsanity.com/paper/2406.00045/) (2024)
- [SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF](https://mlsanity.com/paper/2310.05344/) (2023)
- [A Confederacy of Models: a Comprehensive Evaluation of LLMs on Creative Writing](https://mlsanity.com/paper/2310.08433/) (2023)
- [Decoding-Time Language Model Alignment with Multiple Objectives](https://mlsanity.com/paper/2406.18853/) (2024)
- [Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrievers](https://mlsanity.com/paper/2311.09180/) (2023)
- [Stable LM 2 1.6B Technical Report](https://mlsanity.com/paper/2402.17834/) (2024)
- [The Geometry of Culture: Analyzing Meaning through Word Embeddings](https://mlsanity.com/paper/1803.09288/) (2018)
- [The Metacognitive Demands and Opportunities of Generative AI](https://mlsanity.com/paper/2312.10893/) (2023)
- [Luminate: Structured Generation and Exploration of Design Space with Large Language Models for Human-AI Co-Creation](https://mlsanity.com/paper/2310.12953/) (2023)
- [Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering](https://mlsanity.com/paper/2410.15999/) (2024)
- [Prompting AI Art: An Investigation into the Creative Skill of Prompt Engineering](https://mlsanity.com/paper/2303.13534/) (2023)

## Built on by (most cited first, 1 of 1)

- [ThoughtProbe: Classifier-Guided LLM Thought Space Exploration via Probing Representations](https://mlsanity.com/paper/2510.27355/) (2025)

## Abstract (arXiv)

Personalizing LLM responses typically requires users to articulate their preferences through prompting, which can be burdensome at cold start and difficult to articulate in natural language. We introduce an alternative paradigm, steerable chatbots: rather than asking users to describe what they want, let them directly manipulate it via a linear factor. We implement this through activation steering, leveraging a linear scalar to control how strongly a preference is expressed in the LLM's output. We first assess the computational viability of activation steering as a method to control granular preference expression, then we explore how the factor can be exposed to users. We prototype three activation steering interface designs that vary on the axes of agency (user-led vs. system-driven) and fluidity (static vs. adaptive). A within-subjects user study (n=14) in cold-start personalization tasks shows the potential for steerable chatbots to align better with underlying user preferences than prompting alone, while revealing heterogeneous values around control, persistence, and transparency in LLM personalization.