Tino Weinkauf

Jan Kompatscher, Danqing Shi, Giovanna Varni et al.

Reinforcement learning from human feedback (RLHF) has emerged as a key enabling technology for aligning AI behavior with human preferences. The traditional way to collect data in RLHF is via pairwise comparisons: human raters are asked to indicate which one of two samples they prefer. We present an interactive visualization that better exploits the human visual ability to compare and explore whole groups of samples. The interface is comprised of two linked views: 1) an exploration view showing a contextual overview of all sampled behaviors organized in a hierarchical clustering structure; and 2) a comparison view displaying two selected groups of behaviors for user queries. Users can efficiently explore large sets of behaviors by iterating between these two views. Additionally, we devised an active learning approach suggesting groups for comparison. As shown by our evaluation in six simulated robotics tasks, our approach increases the final policy returns by 69.34%. It leads to lower error rates and better policies. We open-source the code that can be easily integrated into the RLHF training loop, supporting research on human-AI alignment.

Danqing Shi, Furui Cheng, Tino Weinkauf et al.

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 interfaces require annotators to compare text paragraphs, which is cognitively challenging when the texts are long or unfamiliar. This paper contributes by studying the decomposition principle as an approach to improving the quality of human feedback for LLM alignment. This approach breaks down the text into individual claims instead of directly comparing two long-form text responses. Based on the principle, we build a novel user interface DxHF. It enhances the comparison process by showing decomposed claims, visually encoding the relevance of claims to the conversation and linking similar claims. This allows users to skim through key information and identify differences for better and quicker judgment. Our technical evaluation shows evidence that decomposition generally improves feedback accuracy regarding the ground truth, particularly for users with uncertainty. A crowdsourcing study with 160 participants indicates that using DxHF improves feedback accuracy by an average of 5%, although it increases the average feedback time by 18 seconds. Notably, accuracy is significantly higher in situations where users have less certainty. The finding of the study highlights the potential of HCI as an effective method for improving human-AI alignment.

Jan Reininghaus, David Günther, Ingrid Hotz et al.

This paper proposes an efficient probabilistic method that computes combinatorial gradient fields for two dimensional image data. In contrast to existing algorithms, this approach yields a geometric Morse-Smale complex that converges almost surely to its continuous counterpart when the image resolution is increased. This approach is motivated using basic ideas from probability theory and builds upon an algorithm from discrete Morse theory with a strong mathematical foundation. While a formal proof is only hinted at, we do provide a thorough numerical evaluation of our method and compare it to established algorithms.