Danqing Shi

Danqing Shi, Lan Jiang, Katherine M. Collins et al.

The growing prevalence of realistic AI-generated videos on media platforms increasingly blurs the line between fact and fiction, eroding public trust. Understanding how people watch AI-generated videos offers a human-centered perspective for improving AI detection and guiding advancements in video generation. However, existing studies have not investigated human gaze behavior in response to AI-generated videos of physical scenes. Here, we collect and analyze the eye movements from 40 participants during video understanding and AI detection tasks involving a mix of real-world and AI-generated videos. We find that given the high realism of AI-generated videos, gaze behavior is driven less by the video's actual authenticity and more by the viewer's perception of its authenticity. Our results demonstrate that the mere awareness of potential AI generation may alter media consumption from passive viewing into an active search for anomalies.

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.

Xingyu Lan, Leni Yang, Zezhong Wang et al.

Storytelling is an ancient and precious human ability that has been rejuvenated in the digital age. Over the last decade, there has been a notable surge in the recognition and application of data storytelling, both in academia and industry. Recently, the rapid development of generative AI has brought new opportunities and challenges to this field, sparking numerous new questions. These questions may not necessarily be quickly transformed into papers, but we believe it is necessary to promptly discuss them to help the community better clarify important issues and research agendas for the future. We thus invite you to join our workshop (Gen4DS) to discuss questions such as: How can generative AI facilitate the creation of data stories? How might generative AI alter the workflow of data storytellers? What are the pitfalls and risks of incorporating AI in storytelling? We have designed both paper presentations and interactive activities (including hands-on creation, group discussion pods, and debates on controversial issues) for the workshop. We hope that participants will learn about the latest advances and pioneering work in data storytelling, engage in critical conversations with each other, and have an enjoyable, unforgettable, and meaningful experience at the event.

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.

Danqing Shi, Weiwei Cui, Danqing Huang et al.

Visual elements in an information presentation are often spatially and semantically grouped hierarchically for effective message delivery. Studying the hierarchical grouping information can help researchers and designers better explore layout structures and understand design demographics. However, recovering hierarchical grouping is challenging due to a large number of possibilities for compositing visual elements into a single-page design. This paper introduces an automatic approach that takes the layout of visual elements as input and returns the hierarchical grouping as output. To understand information presentations, we first contribute a dataset of 23,072 information presentations with diverse layouts to the community. Next, we propose our technique with a Transformer-based model to predict relatedness between visual elements and a bottom-up algorithm to produce the hierarchical grouping. Finally, we evaluate our technique through a technical experiment and a user study with 30 designers. The results show that the proposed technique is promising.

Yi Guo, Danqing Shi, Mingjuan Guo et al.

Through a natural language interface (NLI) for exploratory visual analysis, users can directly "ask" analytical questions about the given tabular data. This process greatly improves user experience and lowers the technical barriers of data analysis. Existing techniques focus on generating a visualization from a concrete question. However, complex questions, requiring multiple data queries and visualizations to answer, are frequently asked in data exploration and analysis, which cannot be easily solved with the existing techniques. To address this issue, in this paper, we introduce Talk2Data, a natural language interface for exploratory visual analysis that supports answering complex questions. It leverages an advanced deep-learning model to resolve complex questions into a series of simple questions that could gradually elaborate on the users' requirements. To present answers, we design a set of annotated and captioned visualizations to represent the answers in a form that supports interpretation and narration. We conducted an ablation study and a controlled user study to evaluate Talk2Data's effectiveness and usefulness.

Danqing Shi, Xinyue Xu, Fuling Sun et al.

Visual data stories shown in the form of narrative visualizations such as a poster or a data video, are frequently used in data-oriented storytelling to facilitate the understanding and memorization of the story content. Although useful, technique barriers, such as data analysis, visualization, and scripting, make the generation of a visual data story difficult. Existing authoring tools rely on users' skills and experiences, which are usually inefficient and still difficult. In this paper, we introduce a novel visual data story generating system, Calliope, which creates visual data stories from an input spreadsheet through an automatic process and facilities the easy revision of the generated story based on an online story editor. Particularly, Calliope incorporates a new logic-oriented Monte Carlo tree search algorithm that explores the data space given by the input spreadsheet to progressively generate story pieces (i.e., data facts) and organize them in a logical order. The importance of data facts is measured based on information theory, and each data fact is visualized in a chart and captioned by an automatically generated description. We evaluate the proposed technique through three example stories, two controlled experiments, and a series of interviews with 10 domain experts. Our evaluation shows that Calliope is beneficial to efficient visual data story generation.

Danqing Shi, Yang Shi, Xinyue Xu et al.

A chart sequence is used to describe a series of visualization charts generated in the exploratory analysis by data analysts. It provides information details in each chart as well as a logical relationship among charts. While existing research targets on generating chart sequences that match human's perceptions, little attention has been paid to formulate task-oriented connections between charts in a chart design space. We present a novel chart sequencing method based on reinforcement learning to capture the connections between charts in the context of three major analysis tasks, including correlation analysis, anomaly detection, and cluster analysis. The proposed method formulates a chart sequencing procedure as an optimization problem, which seeks an optimal policy to sequencing charts for the specific analysis task. In our method, a novel reward function is introduced, which takes both the analysis task and the factor of human cognition into consideration. We conducted one case study and two user studies to evaluate the effectiveness of our method under the application scenarios of visualization demonstration, sequencing charts for reasoning analysis results, and making a chart design choice. The study results showed the power of our method.