Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lee, Jaewook, Scarlatos, Alexander, Woodhead, Simon, Lan, Andrew
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Simulated Students in Tutoring Dialogues: Substance or Illusion?
by: Scarlatos, Alexander, et al.
Published: (2026)

Who Am I? History-Aware Profiles for Student Simulation in Tutoring Dialogues
by: Duan, Zhangqi, et al.
Published: (2026)

Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues
by: Huang, Shuyan, et al.
Published: (2026)

Training LLM-based Tutors to Improve Student Learning Outcomes in Dialogues
by: Scarlatos, Alexander, et al.
Published: (2025)

Exploring LLMs for Predicting Tutor Strategy and Student Outcomes in Dialogues
by: Ikram, Fareya, et al.
Published: (2025)

Exploring Knowledge Tracing in Tutor-Student Dialogues using LLMs
by: Scarlatos, Alexander, et al.
Published: (2024)

Interpretable Mnemonic Generation for Kanji Learning via Expectation-Maximization
by: Lee, Jaewook, et al.
Published: (2025)

Improving the Validity of Automatically Generated Feedback via Reinforcement Learning
by: Scarlatos, Alexander, et al.
Published: (2024)

Automated Distractor and Feedback Generation for Math Multiple-choice Questions via In-context Learning
by: McNichols, Hunter, et al.
Published: (2023)

Math Multiple Choice Question Generation via Human-Large Language Model Collaboration
by: Lee, Jaewook, et al.
Published: (2024)

Exploring Automated Distractor Generation for Math Multiple-choice Questions via Large Language Models
by: Feng, Wanyong, et al.
Published: (2024)

DiVERT: Distractor Generation with Variational Errors Represented as Text for Math Multiple-choice Questions
by: Fernandez, Nigel, et al.
Published: (2024)

PIIvot: A Lightweight NLP Anonymization Framework for Question-Anchored Tutoring Dialogues
by: Zent, Matthew, et al.
Published: (2025)

RetICL: Sequential Retrieval of In-Context Examples with Reinforcement Learning
by: Scarlatos, Alexander, et al.
Published: (2023)

Gumbel Machine: Counterfactual Student Writing Generation via Gumbel Noise Steering
by: McNichols, Hunter, et al.
Published: (2026)

Misconception Diagnosis From Student-Tutor Dialogue: Generate, Retrieve, Rerank
by: Mitton, Joshua, et al.
Published: (2026)

Evaluating GPT-4 at Grading Handwritten Solutions in Math Exams
by: Caraeni, Adriana, et al.
Published: (2024)

SyllabusQA: A Course Logistics Question Answering Dataset
by: Fernandez, Nigel, et al.
Published: (2024)

CodeGENCAT: Generative Computerized Adaptive Testing for Open-ended Coding Problems
by: Feng, Wanyong, et al.
Published: (2026)

Improving Automated Distractor Generation for Math Multiple-choice Questions with Overgenerate-and-rank
by: Scarlatos, Alexander, et al.
Published: (2024)

Exploring Automated Keyword Mnemonics Generation with Large Language Models via Overgenerate-and-Rank
by: Lee, Jaewook, et al.
Published: (2024)

BILLY: Steering Large Language Models via Merging Persona Vectors for Creative Generation
by: Pai, Tsung-Min, et al.
Published: (2025)

PersoDPO: Scalable Preference Optimization for Instruction-Adherent, Persona-Grounded Dialogue via Multi-LLM Evaluation
by: Afzoon, Saleh, et al.
Published: (2026)

LLMs Are Already Good Tutors: Training-Free Prompt Optimization for Pedagogical Math Tutoring
by: Lee, Unggi, et al.
Published: (2026)

Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
by: Cao, Yuanpu, et al.
Published: (2024)

SMART: Simulated Students Aligned with Item Response Theory for Question Difficulty Prediction
by: Scarlatos, Alexander, et al.
Published: (2025)

EnSToM: Enhancing Dialogue Systems with Entropy-Scaled Steering Vectors for Topic Maintenance
by: Suh, Heejae, et al.
Published: (2025)

Let LLMs Speak Embedding Languages: Generative Text Embeddings via Iterative Contrastive Refinement
by: Tsai, Yu-Che, et al.
Published: (2025)

Score Before You Speak: Improving Persona Consistency in Dialogue Generation using Response Quality Scores
by: Saggar, Arpita, et al.
Published: (2025)

The Impact of Steering Large Language Models with Persona Vectors in Educational Applications
by: Wu, Yongchao, et al.
Published: (2026)

Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors
by: Wang, Weixuan, et al.
Published: (2024)

Training Turn-by-Turn Verifiers for Dialogue Tutoring Agents: The Curious Case of LLMs as Your Coding Tutors
by: Wang, Jian, et al.
Published: (2025)

Let the Fuzzy Rule Speak: Enhancing In-context Learning Debiasing with Interpretability
by: Lin, Ruixi, et al.
Published: (2024)

Exploring Persona Sentiment Sensitivity in Personalized Dialogue Generation
by: Jun, Yonghyun, et al.
Published: (2025)

Leveraging LLMs to Assess Tutor Moves in Real-Life Dialogues: A Feasibility Study
by: Thomas, Danielle R., et al.
Published: (2025)

PicPersona-TOD : A Dataset for Personalizing Utterance Style in Task-Oriented Dialogue with Image Persona
by: Lee, Jihyun, et al.
Published: (2025)

LLM-Independent Adaptive RAG: Let the Question Speak for Itself
by: Marina, Maria, et al.
Published: (2025)

MoCoRP: Modeling Consistent Relations between Persona and Response for Persona-based Dialogue
by: Lee, Kyungro, et al.
Published: (2025)

RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs
by: Dang, John, et al.
Published: (2024)

Teaching According to Students' Aptitude: Personalized Mathematics Tutoring via Persona-, Memory-, and Forgetting-Aware LLMs
by: Wu, Yang, et al.
Published: (2025)