# Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization

arXiv: https://arxiv.org/abs/2602.07639 · HTML: https://mlsanity.com/paper/2602.07639/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Process reward models for reasoning, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 24 of its 42 references that are in the map.
- First posted on arXiv 7 Feb 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Process reward models for reasoning](https://mlsanity.com/alignment/process-reward-models-for-reasoning/)
- Mechanistic interpretability / [Activation steering methods](https://mlsanity.com/mechinterp/activation-steering-methods/)

## Builds on (most cited first, 24 of 24)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models](https://mlsanity.com/paper/2405.01535/) (2024)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering](https://mlsanity.com/paper/2311.06668/) (2023)
- [Personality Traits in Large Language Models](https://mlsanity.com/paper/2307.00184/) (2023)
- [Training Millions of Personalized Dialogue Agents](https://mlsanity.com/paper/1809.01984/) (2018)
- [Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization](https://mlsanity.com/paper/2406.00045/) (2024)
- [Preserving Diversity in Supervised Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2408.16673/) (2024)
- [Exploring Knowledge Tracing in Tutor-Student Dialogues using LLMs](https://mlsanity.com/paper/2409.16490/) (2024)
- [Training LLM-based Tutors to Improve Student Learning Outcomes in Dialogues](https://mlsanity.com/paper/2503.06424/) (2025)
- [AutoTutor meets Large Language Models: A Language Model Tutor with Rich Pedagogy and Guardrails](https://mlsanity.com/paper/2402.09216/) (2024)
- [Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment](https://mlsanity.com/paper/2311.09433/) (2023)
- [Towards the Pedagogical Steering of Large Language Models for Tutoring: A Case Study with Modeling Productive Failure](https://mlsanity.com/paper/2410.03781/) (2024)
- [Improving the Validity of Automatically Generated Feedback via Reinforcement Learning](https://mlsanity.com/paper/2403.01304/) (2024)
- [Pedagogical Alignment of Large Language Models](https://mlsanity.com/paper/2402.05000/) (2024)
- [Simulated Students in Tutoring Dialogues: Substance or Illusion?](https://mlsanity.com/paper/2601.04025/) (2026)
- [From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement Learning](https://mlsanity.com/paper/2505.15607/) (2025)
- [Personality-aware Student Simulation for Conversational Intelligent Tutoring Systems](https://mlsanity.com/paper/2404.06762/) (2024)
- [PIIvot: A Lightweight NLP Anonymization Framework for Question-Anchored Tutoring Dialogues](https://mlsanity.com/paper/2505.16931/) (2025)
- [SPL: A Socratic Playground for Learning Powered by Large Language Model](https://mlsanity.com/paper/2406.13919/) (2024)
- [KASER: Knowledge-Aligned Student Error Simulator for Open-Ended Coding Tasks](https://mlsanity.com/paper/2601.06633/) (2026)

## Built on by (most cited first, 4 of 4)

- [Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues](https://mlsanity.com/paper/2605.01097/) (2026)
- [What Models Express, Suppress, and Resist: Auditing Open-Weight LLMs with Persona Vectors](https://mlsanity.com/paper/2607.13162/) (2026)
- [PIVOT: Preference-based Intervention Vectors for Pedagogical Tutor Steering](https://mlsanity.com/paper/2608.07509/) (2026)
- [Do LLM Tutors Actually Teach? A Process-Centered Synthesis of the Tutoring Loop](https://mlsanity.com/paper/2610.15692/) (2026)

## Abstract (arXiv)

With the emergence of large language models (LLMs) as a powerful class of generative artificial intelligence (AI), their use in tutoring has become increasingly prominent. Prior works on LLM-based tutoring typically learn a single tutor policy and do not capture the diversity of tutoring styles. In real-world tutor-student interactions, pedagogical intent is realized through adaptive instructional strategies, with tutors varying the level of scaffolding, instructional directiveness, feedback, and affective support in response to learners' needs. These differences can all impact dialogue dynamics and student engagement. In this paper, we explore how tutor personas embedded in human tutor-student dialogues can be used to guide LLM behavior without relying on explicitly prompted instructions. We train a steering vector using preference optimization: an activation-space direction that guides model responses toward specific tutor personas. We find that this steering vector captures tutor-specific variation across dialogue contexts, improving semantic alignment with ground-truth tutor utterances and increasing preference-based evaluations, while largely preserving lexical similarity. Analysis of the learned scaling coefficients further reveals interpretable structure across tutors, corresponding to consistent differences in tutoring behavior. These results demonstrate that activation steering offers an effective and interpretable way for controlling tutor-specific variation in LLMs using signals derived directly from human dialogue data.