analiza aiqbench
ParseJargon demonstrates that minimal personalization via single-sentence user profiles significantly outperforms generic definitions in real-time meeting comprehension. The system leverages existing speech-to-text and LLM capabilities to dynamically identify and explain jargon based on individual listener backgrounds. This approach offers a practical path to reducing communication friction in cross-disciplinary online environments without requiring heavy infrastructure.
Breaking the Curse of Knowledge: Designing Personalized Jargon Support for Real-Time Online Meetings
arXiv:2508.10239v3 Announce Type: replace-cross Abstract: Cross-disciplinary communication is often hindered by specialized language (i.e., jargon) and uneven background knowledge. Recent advances in speech-to-text and large language models make it possible to provide jargon support during online meetings, but generic support (i.e., defining the same terms for everyone) can overwhelm listeners with definitions they do not need. We present ParseJargon, a system for personalized jargon support in real-time online meetings. We begin with an initial prototype to probe the use of single-sentence user profiles for personalization. We conducted a controlled study and showed that even this minimal personalization enhanced listeners' comprehension and engagement over generic support because of more precise jargon identification. Guided by insights from participants' feedback, we refined the system with more advanced personalization techniques, including in-session user feedback and portable glossary-based profiles. We evaluated how these techniques can further improve jargon identification precision using data collected in the controlled study to simulate personalization over time. We also conducted a latency test, complemented by a lightweight deployment, to analyze the system's real-time capability and usability.
Abstract:Cross-disciplinary communication is often hindered by specialized language (i.e., jargon) and uneven background knowledge. Recent advances in speech-to-text and large language models make it possible to provide jargon support during online meetings, but generic support (i.e., defining the same terms for everyone) can overwhelm listeners with definitions they do not need. We present ParseJargon, a system for personalized jargon support in real-time online meetings. We begin with an initial prototype to probe the use of single-sentence user profiles for personalization. We conducted a controlled study and showed that even this minimal personalization enhanced listeners' comprehension and engagement over generic support because of more precise jargon identification. Guided by insights from participants' feedback, we refined the system with more advanced personalization techniques, including in-session user feedback and portable glossary-based profiles. We evaluated how these techniques can further improve jargon identification precision using data collected in the controlled study to simulate personalization over time. We also conducted a latency test, complemented by a lightweight deployment, to analyze the system's real-time capability and usability.
Human-Computer Interaction (cs.HC); Computation and Language (cs.CL)
arXiv:2508.10239 [cs.HC]
(or arXiv:2508.10239v3 [cs.HC] for this version)
Text integral sub licența deschisă a publicației · 186 cuvinte
Subiecte conexe
ReGraP-LLaVA: Reasoning enabled Graph-based Personalized Large Language and Vision Assistant
arXiv · 1 sept. 2026
LlamaRec-LKG-RAG: A Single-Pass, Learnable Knowledge Graph-RAG Framework for LLM-Based Ranking
arXiv · 18 aug. 2026
ColaBench: Evaluating Memory-Guided Knowledge Acquisition in Personal Agents
arXiv · 24 oct. 2026
Life-Bench: A Benchmark and Knowledge Graph Framework for Multimodal Personalization Beyond Concept Recognition
arXiv · 1 oct. 2026