6 papers
ChartOptimiser: Task-driven Optimisation of Chart Designs
Yao Wang, Jiarong Pan, Danqing Shi +3
Automated chart design has seen significant advancements with the emergence of Large-Language Models (LLMs), which offer a practical solution for generating charts. However, LLMs f…
Interactive Groupwise Comparison for Reinforcement Learning from Human Feedback
Jan Kompatscher, Danqing Shi, Giovanna Varni +2
Reinforcement learning from human feedback (RLHF) has emerged as a key enabling technology for aligning AI behaviour with human preferences. The traditional way to collect data in…
DxHF: Providing High-Quality Human Feedback for LLM Alignment via Interactive Decomposition
Danqing Shi, Furui Cheng, Tino Weinkauf +2
Human preferences are widely used to align large language models (LLMs) through methods such as reinforcement learning from human feedback (RLHF). However, the current user interfa…
WigglyEyes: Inferring Eye Movements from Keypress Data
Yujun Zhu, Danqing Shi, Hee-Seung Moon +1
We present a model for inferring where users look during interaction based on keypress data only. Given a key log, it outputs a scanpath that tells, moment-by-moment, how the user…
Chartist: Task-driven Eye Movement Control for Chart Reading
Danqing Shi, Yao Wang, Yunpeng Bai +2
To design data visualizations that are easy to comprehend, we need to understand how people with different interests read them. Computational models of predicting scanpaths on char…
Simulating Errors in Touchscreen Typing
Danqing Shi, Yujun Zhu, Francisco Erivaldo Fernandes Junior +2
Empirical evidence shows that typing on touchscreen devices is prone to errors and that correcting them poses a major detriment to users' performance. Design of text entry systems…