paper
Measuring User's Mental Models of Speech Translation in Human-AI Collaboration
paperactiveprovisional
measuring-user-s-mental-models-of-speech-translation-in-human-ai-collaboration-fbd9254f·1 events·first seen 39h agoAliases: Measuring User's Mental Models of Speech Translation in Human-AI Collaboration
More like this (12)
Human-AI Teaming Through the Lens of CalibrationBeyond Accuracy: Community Perspectives on Machine TranslationA Taxonomy of Conceptual Alignment in Human-Robot DialoguePolymathic AI Collaborationsimultaneous speech-to-text translationExploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language ModelsMulti-Faceted Interactivity Alignment in Full-Duplex Speech ModelsHuman-AI Coevolution Dynamics FrameworkCharacterizing Cultural Localization in AI-Generated StoriesApparent Psychological Profiles of Large Language Models are Largely a Measurement ArtifactSame Lesson, Different Story: Cross-Lingual Reconstruction of Cultural Narratives in Large Language ModelsUncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models and GUI Grounding Datasets
Recent events (1)
Framework for measuring users' mental models of machine translation quality in human-AI collaboration
A new arXiv paper introduces a cross-lingual question answering framework to study how users form mental models of speech translation systems, measuring whether users can predict where MT output is likely to be wrong. The study finds that users develop stronger mental models with practice, particularly when they have some source-language knowledge or access to speech transcriptions. Results suggest cross-lingual QA is a viable downstream task for studying human-AI collaboration in translation contexts.