# ExPerT: Personalizing LLM Responses to Users' Domain Expertise via Query-Wise Semantic and Keystroke Behavioral Cues

arXiv: https://arxiv.org/abs/2607.01242 · HTML: https://mlsanity.com/paper/2607.01242/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 50 references that are in the map.
- First posted on arXiv 4 May 2026.

## Builds on (most cited first, 29 of 29)

- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Tensor Fusion Network for Multimodal Sentiment Analysis](https://mlsanity.com/paper/1707.07250/) (2017)
- [Efficient Low-rank Multimodal Fusion with Modality-Specific Factors](https://mlsanity.com/paper/1806.00064/) (2018)
- [Active Example Selection for In-Context Learning](https://mlsanity.com/paper/2211.04486/) (2022)
- [Quantifying the Persona Effect in LLM Simulations](https://mlsanity.com/paper/2402.10811/) (2024)
- [Memory Fusion Network for Multi-view Sequential Learning](https://mlsanity.com/paper/1802.00927/) (2018)
- [Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning](https://mlsanity.com/paper/2408.10075/) (2024)
- [Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs](https://mlsanity.com/paper/2502.09597/) (2025)
- [ExpertPrompting: Instructing Large Language Models to be Distinguished Experts](https://mlsanity.com/paper/2305.14688/) (2023)
- [Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debate](https://mlsanity.com/paper/2305.13160/) (2023)
- [Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs](https://mlsanity.com/paper/2305.11792/) (2023)
- [Determinants of LLM-assisted Decision-Making](https://mlsanity.com/paper/2402.17385/) (2024)
- [How Many Demonstrations Do You Need for In-context Learning?](https://mlsanity.com/paper/2303.08119/) (2023)
- [Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinement](https://mlsanity.com/paper/2402.11060/) (2024)
- [Knowledge-Augmented Large Language Models for Personalized Contextual Query Suggestion](https://mlsanity.com/paper/2311.06318/) (2023)
- [Augmenting Scientific Papers with Just-in-Time, Position-Sensitive Definitions of Terms and Symbols](https://mlsanity.com/paper/2009.14237/) (2020)
- [AI PERSONA: Towards Life-long Personalization of LLMs](https://mlsanity.com/paper/2412.13103/) (2024)
- [Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answering](https://mlsanity.com/paper/2311.06503/) (2023)
- [On the Way to LLM Personalization: Learning to Remember User Conversations](https://mlsanity.com/paper/2411.13405/) (2024)
- [ScatterShot: Interactive In-context Example Curation for Text Transformation](https://mlsanity.com/paper/2302.07346/) (2023)
- ["In Dialogues We Learn": Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning](https://mlsanity.com/paper/2403.03102/) (2024)
- [Combating Human Trafficking with Deep Multimodal Models](https://mlsanity.com/paper/1705.02735/) (2017)
- [ScholaWrite: A Dataset of End-to-End Scholarly Writing Process](https://mlsanity.com/paper/2502.02904/) (2025)
- [Keystroke dynamics as signal for shallow syntactic parsing](https://mlsanity.com/paper/1610.03321/) (2016)
- [Enabling On-Device LLMs Personalization with Smartphone Sensing](https://mlsanity.com/paper/2407.04418/) (2024)
- [The Impact of Technical Domain Expertise on Search Behavior and Task Outcome](https://mlsanity.com/paper/1512.07051/) (2015)
- [Dynamic Context-Aware Prompt Recommendation for Domain-Specific AI Applications](https://mlsanity.com/paper/2506.20815/) (2025)
- [Experts prefer text but videos help novices: an analysis of the utility of multi-media content](https://mlsanity.com/paper/2304.11565/) (2023)
- [Speaking the Right Language: The Impact of Expertise Alignment in User-AI Interactions](https://mlsanity.com/paper/2502.18685/) (2025)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used by end users, yet existing personalization methods relying on static profiles or text-only signals fail to capture query-specific expertise variation. We present ExPerT, a query-wise personalization framework that adapts LLM responses to users' query domain expertise by combining semantic and behavioral cues. ExPerT consists of two key components: (i) a semantic-behavioral expertise inference module that jointly interprets query text and keystroke dynamics via in-context LLM prompting, and (ii) an expertise-conditioned response generation that adapts the level of detail, terminology, and conceptual complexity. Our user study with 40 participants and 1270 queries demonstrated that ExPerT reduced expertise inference error by 65.7% compared to the strongest baseline (MAE = 0.398 vs. 1.162) and improved response satisfaction by 17.52% (from 3.71 to 4.36) on a 5-point Likert scale.