ExPerT: Personalizing LLM Responses to Users' Domain Expertise via Query-Wise Semantic and Keystroke Behavioral Cues
Not on the map. Why?
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 50 references that are in the map. First posted on arXiv 4 May 2026.
Builds on
29 of 50 references.
References · 29
- 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
- 2017Tensor Fusion Network for Multimodal Sentiment Analysiscited by 429
- 2018Efficient Low-rank Multimodal Fusion with Modality-Specific Factorscited by 268
- 2022Active Example Selection for In-Context Learningcited by 195
- 2018Memory Fusion Network for Multi-view Sequential Learningcited by 167
- 2024Quantifying the Persona Effect in LLM Simulationscited by 164
- 2024Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learningcited by 147
- 2025Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMscited by 142
- 2023ExpertPrompting: Instructing Large Language Models to be Distinguished Expertscited by 140
- 2023Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debatecited by 92
- 2023Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMscited by 62
- 2024Determinants of LLM-assisted Decision-Makingcited by 55
17 more
- 2023How Many Demonstrations Do You Need for In-context Learning?cited by 52
- 2024Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinementcited by 47
- 2023Knowledge-Augmented Large Language Models for Personalized Contextual Query Suggestioncited by 43
- 2020Augmenting Scientific Papers with Just-in-Time, Position-Sensitive Definitions of Terms and Symbolscited by 36
- 2024AI PERSONA: Towards Life-long Personalization of LLMscited by 30
- 2023Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answeringcited by 28
- 2024On the Way to LLM Personalization: Learning to Remember User Conversationscited by 21
- 2023ScatterShot: Interactive In-context Example Curation for Text Transformationcited by 20
- 2024"In Dialogues We Learn": Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learningcited by 10
- 2017Combating Human Trafficking with Deep Multimodal Modelscited by 9
- 2016Keystroke dynamics as signal for shallow syntactic parsingcited by 8
- 2025ScholaWrite: A Dataset of End-to-End Scholarly Writing Processcited by 8
- 2024Enabling On-Device LLMs Personalization with Smartphone Sensingcited by 6
- 2015The Impact of Technical Domain Expertise on Search Behavior and Task Outcomecited by 2
- 2025Dynamic Context-Aware Prompt Recommendation for Domain-Specific AI Applicationscited by 2
- 2023Experts prefer text but videos help novices: an analysis of the utility of multi-media contentcited by 1
- 2025Speaking the Right Language: The Impact of Expertise Alignment in User-AI Interactionscited by 1
Built on by
Not cited yet.