mlsanityData to 14 Oct 2026

Is Passive Expertise-Based Personalization Enough? A Case Study in AI-Assisted Test-Taking

arXiv 2511.23376 ↗First posted 28 Nov 2025cs.HC cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

Novice and expert users have different systematic preferences in task-oriented dialogues. However, whether catering to these preferences actually improves user experience and task performance remains understudied. To investigate the effects of expertise-based personalization, we first built a version of an enterprise AI assistant with passive personalization. We then conducted a user study where participants completed timed exams, aided by the two versions of the AI assistant. Preliminary results indicate that passive personalization helps reduce task load and improve assistant perception, but reveal task-specific limitations that can be addressed through providing more user agency. These findings underscore the importance of combining active and passive personalization to optimize user experience and effectiveness in enterprise task-oriented environments.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 18 of its 48 references that are in the map. First posted on arXiv 28 Nov 2025.

Builds on

18 of 48 references.

References · 18

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023LaMP: When Large Language Models Meet Personalizationcited by 437
  3. 2024Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programscited by 291
  4. 2024Hello Again! LLM-powered Personalized Agent for Long-term Dialoguecited by 123
  5. 2023Conversational Health Agents: A Personalized LLM-Powered Agent Frameworkcited by 92
  6. 2019Personalized Dialogue Generation with Diversified Traitscited by 74
  7. 2024Exploring Knowledge Tracing in Tutor-Student Dialogues using LLMscited by 46
  8. 2023Learning to Rewrite Prompts for Personalized Text Generationcited by 40
  9. 2022Advancing Human-AI Complementarity: The Impact of User Expertise and Algorithmic Tuning on Joint Decision Makingcited by 33
  10. 2017Personalization in Goal-Oriented Dialogcited by 29
  11. 2024Doing Personal LAPS: LLM-Augmented Dialogue Construction for Personalized Multi-Session Conversational Searchcited by 24
  12. 2024Learning Agent-based Modeling with LLM Companions: Experiences of Novices and Experts Using ChatGPT & NetLogo Chatcited by 23
6 more
  1. 2024Towards Modeling Learner Performance with Large Language Modelscited by 21
  2. 2018Learning Personalized End-to-End Goal-Oriented Dialogcited by 19
  3. 2024CLST: Cold-Start Mitigation in Knowledge Tracing by Aligning a Generative Language Model as a Students' Knowledge Tracercited by 17
  4. 2025ELI-Why: Evaluating the Pedagogical Utility of Language Model Explanationscited by 4
  5. 2025ProfiLLM: An LLM-Based Framework for Implicit Profiling of Chatbot Userscited by 3
  6. 2015The Impact of Technical Domain Expertise on Search Behavior and Task Outcomecited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Beyond Direct Identifiers: Probabilistic Privacy Risk Estimation for Privacy-Conscious LLM Query Delegationcited by 2