3 papers
cs.LG2025
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…
cs.GR2025
A Comparative Study of Different Edit Distance-Based Methods for Feature Tracking using Merge Trees on Time-Varying Scalar Fields
Son Le Thanh, Tino Weinkauf
Feature tracking in time-varying scalar fields is a fundamental task in scientific computing. Topological descriptors, which summarize important features of data, have proved to be…
cs.HC2025
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…