arXiv subjects

Songheng Zhang

Publications and source records attributed to Songheng Zhang.

10 recordsLinked to original sources

arXiv2026

UncertaintyVis: Preserving Linguistic Uncertainty in Automated Text-to-Chart Generation

Data-rich documents pair narrative text with quantitative claims, and authors routinely qualify those claims with linguistic uncertainty markers such as "nearly," "approximately," or "at least." Automated text-to-chart systems discard these markers, producing visualizations that appear definitive even when the source text expresses hedged or incomplete knowledge. Readers may then over-interpret precision and misjudge author intent. We present UncertaintyVis, a system that preserves linguistic uncertainty during automated chart generation. A formative corpus analysis of 211 uncertainty expressions across 12 documents and 8 domains yielded a four-category taxonomy: Surface Form Normalization, Precision Boundaries, Inferential Derivation, and Non-Inferable Gaps. We mapped each category to chart-specific visual encodings that signal uncertainty without disturbing the spatial integrity readers rely on, and implemented an end-to-end pipeline pairing large language model text analysis with uncertainty-aware rendering. In a two-part study with 12 participants, readers matched charts to source text with 85% accuracy and text to charts with 76%. Uncertainty-aware visualizations trended toward lower cognitive demand (effect sizes 0.460 and 0.769 for mental demand and effort), and 75% of participants preferred them to plain text, describing explicit uncertainty encodings as a basis for verifying data claims. Encoding effectiveness varied by chart type: bar and pie encodings performed consistently, while line chart encodings require redesign.

cs.HC↗

arXiv2026

CogBias: Measuring and Mitigating Cognitive Bias in Large Language Models

Large Language Models (LLMs) are increasingly deployed in high-stakes decision-making contexts. While prior work has shown that LLMs exhibit cognitive biases behaviorally, whether these biases correspond to identifiable internal representations and can be mitigated through targeted intervention remains an open question. We define LLM cognitive bias as systematic, reproducible deviations from correct answers in tasks with computable ground-truth baselines, and introduce LLM CogBias, a benchmark organized around four families of cognitive biases: Judgment, Information Processing, Social, and Response. We evaluate three LLMs and find that cognitive biases emerge systematically across all four families, with magnitudes and debiasing responses that are strongly family-dependent: prompt-level debiasing substantially reduces Response biases but backfires for Judgment biases. Using linear probes under a contrastive design, we show that these biases are encoded as linearly separable directions in model activation space. Finally, we apply activation steering to modulate biased behavior, achieving 26--32\% reduction in bias score (fraction of biased responses) while preserving downstream capability on 25 benchmarks (Llama: negligible degradation; Qwen: up to $-$19.0pp for Judgment biases). Despite near-orthogonal bias representations across models (mean cosine similarity 0.01), steering reduces bias at similar rates across architectures ($r(246)$=.621, $p$<.001), suggesting shared functional organization.

cs.AI↗

arXiv2026

BAIT: Visual-illusion-inspired Privacy Preservation for Mobile Data Visualization

With the prevalence of mobile data visualizations, there have been growing concerns about their privacy risks, especially shoulder surfing attacks. Inspired by prior research on visual illusion, we propose BAIT, a novel approach to automatically generate privacy-preserving visualizations by stacking a decoy visualization over a given visualization. It allows visualization owners at proximity to clearly discern the original visualization and makes shoulder surfers at a distance be misled by the decoy visualization, by adjusting different visual channels of a decoy visualization (e.g., shape, position, tilt, size, color and spatial frequency). We explicitly model human perception effect at different viewing distances to optimize the decoy visualization design. Privacy-preserving examples and two in-depth user studies demonstrate the effectiveness of BAIT in both controlled lab study and real-world scenarios.

cs.HC↗

arXiv2026

Chameleon: Automated Color Palette Adaptation for Dark Mode Data Visualizations

Dark mode has gained widespread adoption across mobile platforms due to its benefits in reducing eye strain and conserving battery life. However, while the mobile system switches to dark mode, most visualizations remain designed for light mode, causing visual disruptions. Existing methods, such as manual adjustment or color inversion, are either time-consuming or fail to preserve the semantic meaning of colors in visualizations, making them less effective in dark mode. To address this challenge, we propose Chameleon, an algorithm that automatically transforms light mode visualizations into dark mode while maintaining visual clarity and color semantics. By optimizing for luminance contrast, color consistency, and adjacent color differences, Chameleon ensures that the transformed visualizations are legible and visually coherent. Our evaluation includes case study, expert interview, system evaluation, and a user study, and these demonstrate that Chameleon is effective at translating visualizations for dark mode.

cs.HC↗

arXiv2024

ChartifyText: Automated Chart Generation from Data-Involved Texts via LLM

Text documents with numerical values involved are widely used in various applications such as scientific research, economy, public health and journalism. However, it is difficult for readers to quickly interpret such data-involved texts and gain deep insights. To fill this research gap, this work aims to automatically generate charts to accurately convey the underlying data and ideas to readers, which is essentially a challenging task. The challenges originate from text ambiguities, intrinsic sparsity and uncertainty of data in text documents, and subjective sentiment differences. Specifically, we propose ChartifyText, a novel fully-automated approach that leverages Large Language Models (LLMs) to convert complex data-involved texts to expressive charts. It consists of two major modules: tabular data inference and expressive chart generation. The tabular data inference module employs systematic prompt engineering to guide the LLM (e.g., GPT-4) to infer table data, where data ranges, uncertainties, missing data values and corresponding subjective sentiments are explicitly considered. The expressive chart generation module augments standard charts with intuitive visual encodings and concise texts to accurately convey the underlying data and insights. We extensively evaluate the effectiveness of ChartifyText on real-world data-involved text documents through case studies, in-depth interviews with three visualization experts, and a carefully-designed user study with 15 participants. The results demonstrate the usefulness and effectiveness of ChartifyText in helping readers efficiently and effectively make sense of data-involved texts.

cs.HC↗

arXiv2023

AdaVis: Adaptive and Explainable Visualization Recommendation for Tabular Data

Automated visualization recommendation facilitates the rapid creation of effective visualizations, which is especially beneficial for users with limited time and limited knowledge of data visualization. There is an increasing trend in leveraging machine learning (ML) techniques to achieve an end-to-end visualization recommendation. However, existing ML-based approaches implicitly assume that there is only one appropriate visualization for a specific dataset, which is often not true for real applications. Also, they often work like a black box, and are difficult for users to understand the reasons for recommending specific visualizations. To fill the research gap, we propose AdaVis, an adaptive and explainable approach to recommend one or multiple appropriate visualizations for a tabular dataset. It leverages a box embedding-based knowledge graph to well model the possible one-to-many mapping relations among different entities (i.e., data features, dataset columns, datasets, and visualization choices). The embeddings of the entities and relations can be learned from dataset-visualization pairs. Also, AdaVis incorporates the attention mechanism into the inference framework. Attention can indicate the relative importance of data features for a dataset and provide fine-grained explainability. Our extensive evaluations through quantitative metric evaluations, case studies, and user interviews demonstrate the effectiveness of AdaVis.

cs.HC↗

arXiv2023

LLM4Vis: Explainable Visualization Recommendation using ChatGPT

Data visualization is a powerful tool for exploring and communicating insights in various domains. To automate visualization choice for datasets, a task known as visualization recommendation has been proposed. Various machine-learning-based approaches have been developed for this purpose, but they often require a large corpus of dataset-visualization pairs for training and lack natural explanations for their results. To address this research gap, we propose LLM4Vis, a novel ChatGPT-based prompting approach to perform visualization recommendation and return human-like explanations using very few demonstration examples. Our approach involves feature description, demonstration example selection, explanation generation, demonstration example construction, and inference steps. To obtain demonstration examples with high-quality explanations, we propose a new explanation generation bootstrapping to iteratively refine generated explanations by considering the previous generation and template-based hint. Evaluations on the VizML dataset show that LLM4Vis outperforms or performs similarly to supervised learning models like Random Forest, Decision Tree, and MLP in both few-shot and zero-shot settings. The qualitative evaluation also shows the effectiveness of explanations generated by LLM4Vis. We make our code publicly available at \href{https://github.com/demoleiwang/LLM4Vis}{https://github.com/demoleiwang/LLM4Vis}.

cs.HC↗

arXiv2023

Don't Peek at My Chart: Privacy-preserving Visualization for Mobile Devices

Data visualizations have been widely used on mobile devices like smartphones for various tasks (e.g., visualizing personal health and financial data), making it convenient for people to view such data anytime and anywhere. However, others nearby can also easily peek at the visualizations, resulting in personal data disclosure. In this paper, we propose a perception-driven approach to transform mobile data visualizations into privacy-preserving ones. Specifically, based on human visual perception, we develop a masking scheme to adjust the spatial frequency and luminance contrast of colored visualizations. The resulting visualization retains its original information in close proximity but reduces the visibility when viewed from a certain distance or further away. We conducted two user studies to inform the design of our approach (N=16) and systematically evaluate its performance (N=18), respectively. The results demonstrate the effectiveness of our approach in terms of privacy preservation for mobile data visualizations.

cs.HC↗

arXiv2022

Who Will Support My Project? Interactive Search of Potential Crowdfunding Investors Through InSearch

Crowdfunding provides project founders with a convenient way to reach online investors. However, it is challenging for founders to find the most potential investors and successfully raise money for their projects on crowdfunding platforms. A few machine learning based methods have been proposed to recommend investors' interest in a specific crowdfunding project, but they fail to provide project founders with explanations in detail for these recommendations, thereby leading to an erosion of trust in predicted investors. To help crowdfunding founders find truly interested investors, we conducted semi-structured interviews with four crowdfunding experts and presents inSearch, a visual analytic system. inSearch allows founders to search for investors interactively on crowdfunding platforms. It supports an effective overview of potential investors by leveraging a Graph Neural Network to model investor preferences. Besides, it enables interactive exploration and comparison of the temporal evolution of different investors' investment details.

cs.HC↗

arXiv2021

KG4Vis: A Knowledge Graph-Based Approach for Visualization Recommendation

Visualization recommendation or automatic visualization generation can significantly lower the barriers for general users to rapidly create effective data visualizations, especially for those users without a background in data visualizations. However, existing rule-based approaches require tedious manual specifications of visualization rules by visualization experts. Other machine learning-based approaches often work like black-box and are difficult to understand why a specific visualization is recommended, limiting the wider adoption of these approaches. This paper fills the gap by presenting KG4Vis, a knowledge graph (KG)-based approach for visualization recommendation. It does not require manual specifications of visualization rules and can also guarantee good explainability. Specifically, we propose a framework for building knowledge graphs, consisting of three types of entities (i.e., data features, data columns and visualization design choices) and the relations between them, to model the mapping rules between data and effective visualizations. A TransE-based embedding technique is employed to learn the embeddings of both entities and relations of the knowledge graph from existing dataset-visualization pairs. Such embeddings intrinsically model the desirable visualization rules. Then, given a new dataset, effective visualizations can be inferred from the knowledge graph with semantically meaningful rules. We conducted extensive evaluations to assess the proposed approach, including quantitative comparisons, case studies and expert interviews. The results demonstrate the effectiveness of our approach.

cs.HC↗