HCI.TOPHCI, made easy

arrow_backBack to questions View categoryarrow_forward

Data Annotation, Model Debugging, and Data Work / Contextual Example Selection and Rare Pattern Coverage

Users struggle to cover rare patterns when selecting in-context examples, leading to unstable model performance.

lightbulbPractical problemContextual Example Selection and Rare Pattern Coverage

Users struggle to cover rare patterns when selecting in-context examples, leading to unstable model performance.

IUI '23ScatterShot: Interactive In-context Example Curation for Text Transformation

Similar questions

lightbulbPractical problemContextual Example Selection and Rare Pattern Coverage

Children lack suitable AI learning tools to effectively master AI fundamentals.

CHI '25Technologies for Children’s AI Learning: Design Features and Future Opportunities

lightbulbPractical problemContextual Example Selection and Rare Pattern Coverage

Students in online education struggle to actively ask questions and explore knowledge from video-based learning.

CHI '25From Passive Watching to Active Learning: Empowering Proactive Participation in Digital Classrooms with AI Video Assistant

lightbulbPractical problemContextual Example Selection and Rare Pattern Coverage

Users often overgeneralize complex data due to confirmation bias, leading to suboptimal decisions.

CHI '25Confirmation Bias: The Double-Edged Sword of Data Facts in Visual Data Communication

lightbulbPractical problemContextual Example Selection and Rare Pattern Coverage

Data slicing and model optimization depend on metadata, making operations complex and costly.

IUI '24Slicing, Chatting, and Refining: A Concept-Based Approach for Machine Learning Model Validation with ConceptSlicer

lightbulbPractical problemContextual Example Selection and Rare Pattern Coverage

WiFi activity recognition struggles to adapt across environments and individuals and requires large amounts of labeled data.

UbiComp '24MetaFormer: Domain-Adaptive WiFi Sensing with Only One Labelled Target Sample

lightbulbPractical problemContextual Example Selection and Rare Pattern Coverage

Users frequently decline proactive learning tasks from smart speakers due to poor timing.

CHI '24Interrupting for Microlearning: Understanding Perceptions and Interruptibility of Proactive Conversational Microlearning Services

Related papers

Technologies for Children’s AI Learning: Design Features and Future Opportunities

Kaiyue Jia, Junnan Yu

From Passive Watching to Active Learning: Empowering Proactive Participation in Digital Classrooms with AI Video Assistant

Anna Bodonhelyi, Enkeleda Thaqi, Süleyman Özdel

Confirmation Bias: The Double-Edged Sword of Data Facts in Visual Data Communication

Shiyao Li, Thomas James Davidson, Cindy Xiong Bearfield

Slicing, Chatting, and Refining: A Concept-Based Approach for Machine Learning Model Validation with ConceptSlicer

Xiaoyu Zhang, Jorge H Piazentin Ono, Wenbin He

MetaFormer: Domain-Adaptive WiFi Sensing with Only One Labelled Target Sample

Biyun Sheng, Rui Han, Fu Xiao

Interrupting for Microlearning: Understanding Perceptions and Interruptibility of Proactive Conversational Microlearning Services

Minyeong Kim, Jiwook Lee, Youngji Koh

AMIR: Active Multimodal Interaction Recognition from Video and Network Traffic in Connected Environments

Shinan Liu, Tarun Mangla, Ted Shaowang

A Dialogue-Based Interface for Active Learning of Activities of Daily Living

Ronnie Smith, Mauro Dragone