arXiv subjects

Dazhen Deng

Publications and source records attributed to Dazhen Deng.

At least 19 recordsLinked to original sources

arXiv2026

DashArena: Benchmarking LLMs on Interactive Analytic Dashboard Generation

Analytic dashboards combine coordinated views and interactions for data exploration and decision-making. Recent models can generate them from data and natural-language goals, but evaluating their usefulness remains difficult. Dashboard generation is open-ended, and neither static appearance nor successful execution alone captures analytical support and interaction quality. We introduce DashArena, to our knowledge the first benchmark for open-ended, task-grounded generation of interactive analytic dashboards. Its key innovation is to require each system to generate both a dashboard and a replayable interaction trajectory. A browser executor replays the trajectory and turns the system's intended analytical workflow into reproducible visual and execution evidence. A VLM judge compares candidates using this evidence, and Bradley--Terry aggregation produces the leaderboard. We further distill the judge into the open-weight DashJudge-8B. Human evaluations show that DashJudge-8B effectively reproduces human judgments and ablations show that interaction evidence improves judge agreement. Experiments with frontier models reveal persistent rendering, analytical, and interaction failures. Together, these results show that realistic dashboard generation remains challenging and that interaction-aware evaluation captures failures missed by static or execution-only checks.

cs.AI↗

arXiv2026

Making Multimodal LLMs Reliable Chart Data Extractors: A Benchmark and Training Framework

Chart data extraction, which reverse-engineers data tables from chart images, is essential for reproducibility, analysis, retrieval, and redesign. Existing interactive tools are reliable but tedious, and mixed-initiative systems, while more efficient, lack generalizability. Recent multimodal large language models (MLLMs) offer a unified interface for chart interpretation, yet their ability to extract accurate data tables, especially without visible labels, remains unclear. We build a benchmark featuring diverse real-world charts without data labels to evaluate this capability. Results show that, while current MLLMs reliably reconstruct table structures, they struggle with precise value recovery. To address this, we revisit chart data extraction from a human-centered perspective and argue that extraction should follow a progressive learning process similar to how people read charts. Our training framework substantially improves numerical accuracy, achieving state-of-the-art performance with a 7B-parameter model. A user study further shows that our model effectively supports mixed-initiative workflows for reliable chart data extraction.

cs.HC↗

arXiv2026

Crystalis: Progressive Nucleation and Semantic Annealing for Coordinated Multi-View Visualization Generation

Large language models (LLMs) can generate individual charts, but coordinated multi-view visualizations (CMVs), where views share data flows and cross-view interactions, remain out of reach. Tight field-level coupling among data transformations, visual encodings, and interaction coordinations causes errors in one component to silently invalidate others. Rather than pursuing end-to-end analytical quality, which depends on model capability, domain knowledge, and user expertise, we target a foundational question: can LLMs reliably produce structurally correct CMVs, and what abstractions make this possible? We present Crystalis, a framework built on query-centric CMV modeling that decomposes a CMV into structured queries over a dependency graph spanning three component types (Data, Visualization, Interaction) and three abstraction levels (requirement, specification, executable object). Two complementary mechanisms operate over this structure: progressive nucleation crystallizes each query vertically from requirement to object along the dependency order, while semantic annealing enforces horizontal consistency across queries at each level through layered logical checks. On a 12-task benchmark across five frontier LLMs, Crystalis achieves up to 75% end-to-end success, substantially outperforming an agentic coding baseline (8.3% E2E with the same foundation model), and a user study with 12 practitioners confirms the usability of the decomposition and iterative refinement workflow.

cs.AI↗

arXiv2026

ProSPy: A Profiling-Driven SQL-Python Agentic Framework for Enterprise Text-to-SQL

Large language models have substantially advanced Text-to-SQL systems, yet applying them to enterprise-scale databases remains challenging. Real-world databases often contain large and heterogeneous schemas, incomplete metadata, dialect-specific SQL syntax, and complex analytical questions that are difficult to solve with a single SQL query. To address these challenges, we propose ProSPy, a Profiling-driven SQL--Python agentic framework for enterprise-scale Text-to-SQL. ProSPy structures the reasoning process into four stages: it first extracts fine-grained data evidence through automatic profiling, progressively prunes large schemas into task-relevant contexts, fetches intermediate views through a dialect-agnostic SQL interface, and finally performs flexible downstream analysis with Python. This design combines the efficiency of SQL over large databases with the flexibility of Python-based analysis, while reducing reliance on unreliable metadata and improving robustness across SQL dialects. Experiments on Spider 2.0-Lite and Spider 2.0-Snow show that ProSPy consistently outperforms strong baselines with both open-source and proprietary models, achieving execution accuracies of 60.15% and 60.51% with Claude-4.5-Opus, without majority voting. Further analysis shows that ProSPy is robust to SQL dialect variations and achieves a favorable trade-off between schema recall and precision.

cs.CL↗

arXiv2026

EviLink: Multi-Path Schema Linking with Uncertainty-Guided Evidence Acquisition for Large-Scale Text-to-SQL

Schema linking is a difficult and important step in large-scale Text-to-SQL, where systems must identify a compact yet sufficient schema context from large and ambiguous databases. Existing methods often treat schema linking as deterministic selection around a single SQL path, but complex questions may admit multiple valid realizations with different schema needs. We reframe schema linking as uncertainty-aware schema-need inference over multiple plausible SQL paths, where the system distinguishes required schema items from path-dependent uncertain ones and acquires evidence only where needed. We instantiate this reframing with EviLink, which combines multi-hypothesis schema grounding with uncertainty-guided evidence acquisition. Experiments on BIRD-Dev and Spider2-Snow show that this perspective improves the balance among schema completeness, schema relevance, and token cost. On Spider2-Snow, EviLink achieves 90.15% field-level strict recall rate, uses 123.30K average tokens, and improves downstream SQL generation under a fixed generator.

cs.CL↗

arXiv2026

GraphTide: Augmenting Knowledge-Intensive Text with Progressive Nested Graph

Knowledge-intensive text usually contains fruitful entities and complex relationships, such as academic articles and scientific exposition. Reading and comprehending such texts often demands considerable time and mental effort to track the relationships between entities. To reduce the burden, we present GraphTide, a visualization technique that progressively constructs nested entity-relationship graphs with animation to support the understanding of complex text. Our method features an on-demand entity-relationship decomposition pipeline that constructs nested graphs to represent intra- and inter-sentence relationships. Moreover, we propose a structure-aware force-directed layout optimization algorithm to enhance structural clarity. Sentences and their associated entities are incrementally revealed through animated transitions, helping users maintain context as the narrative unfolds. A user study shows that GraphTide significantly improves users' comprehension of knowledge-intensive texts compared to traditional graph-based techniques and static nested graph representations.

cs.HC↗

arXiv2026

KEditVis: A Visual Analytics System for Knowledge Editing of Large Language Models

Large Language Models (LLMs) demonstrate exceptional capabilities in factual question answering, yet they sometimes provide incorrect responses. To address this issue, knowledge editing techniques have emerged as effective methods for correcting factual information in LLMs. However, typical knowledge editing workflows struggle with identifying the optimal set of model layers for editing and rely on summary indicators that provide insufficient guidance. This lack of transparency hinders effective comparison and identification of optimal editing strategies. In this paper, we present KEditVis, a novel visual analytics system designed to assist users in gaining a deeper understanding of knowledge editing through interactive visualizations, improving editing outcomes, and discovering valuable insights for the future development of knowledge editing algorithms. With KEditVis, users can select appropriate layers as the editing target, explore the reasons behind ineffective edits, and perform more targeted and effective edits. Our evaluation, including usage scenarios, expert interviews, and a user study, validates the effectiveness and usability of the system.

cs.HC↗

arXiv2026

Do LLM-Driven Agents Exhibit Engagement Mechanisms? Controlled Tests of Information Load, Descriptive Norms, and Popularity Cues

Large language models make agent-based simulation more behaviorally expressive, but they also sharpen a basic methodological tension: fluent, human-like output is not, by itself, evidence for theory. We evaluate what an LLM-driven simulation can credibly support using information engagement on social media as a test case. In a Weibo-like environment, we manipulate information load and descriptive norms, while allowing popularity cues (cumulative likes and Sina Weibo-style cumulative reshares) to evolve endogenously. We then ask whether simulated behavior changes in theoretically interpretable ways under these controlled variations, rather than merely producing plausible-looking traces. Engagement responds systematically to information load and descriptive norms, and sensitivity to popularity cues varies across contexts, indicating conditionality rather than rigid prompt compliance. We discuss methodological implications for simulation-based communication research, including multi-condition stress tests, explicit no-norm baselines because default prompts are not blank controls, and design choices that preserve endogenous feedback loops when studying bandwagon dynamics.

cs.AI↗

arXiv2026

StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation

Large language models (LLMs) are increasingly applied in specialized domains such as finance and healthcare, where they introduce unique safety risks. Domain-specific datasets of harmful prompts remain scarce and still largely rely on manual construction; public datasets mainly focus on explicit harmful prompts, which modern LLM defenses can often detect and refuse. In contrast, implicit harmful prompts-expressed through indirect domain knowledge-are harder to detect and better reflect real-world threats. We identify two challenges: transforming domain knowledge into actionable constraints and increasing the implicitness of generated harmful prompts. To address them, we propose an end-to-end framework that first performs knowledge-graph-guided harmful prompt generation to systematically produce domain-relevant prompts, and then applies two-strategy obfuscation rewriting to convert explicit harmful prompts into implicit variants via direct and context-enhanced rewriting. This framework yields high-quality datasets combining strong domain relevance with implicitness, enabling more realistic red-teaming and advancing LLM safety research. We release our code and datasets on GitHub.

cs.CL↗

arXiv2025

CycleChart: A Unified Consistency-Based Learning Framework for Bidirectional Chart Understanding and Generation

Current chart-related tasks, such as chart generation (NL2Chart), chart schema parsing, chart data parsing, and chart question answering (ChartQA), are typically studied in isolation, preventing models from learning the shared semantics that link chart creation and interpretation. We introduce CycleChart, a consistency-based learning framework for bidirectional chart understanding and generation. Unlike conventional multi-task approaches that draw training samples independently across tasks, CycleChart organizes all tasks around each single data instance. From a source table and natural-language query, the model generates a chart specification, renders and executes it, then learns to recover the schema and underlying data from the resulting chart image. This per-instance lifecycle design lets the model capture the full chain of transformations, from raw data through visual encoding to structured recovery, and a generate--parse consistency objective enforces semantic alignment between the forward generation and reverse parsing directions. To support this framework, we construct CycleChart-Bench, a lifecycle-aligned benchmark where every chart sample carries aligned annotations for generation, schema parsing, data parsing, and question answering. CycleChart achieves strong results across all four tasks and transfers effectively to unseen external benchmarks, demonstrating improved cross-task generalization and marking a step toward more general chart understanding models.

cs.CL↗

arXiv2025

Linking Heterogeneous Data with Coordinated Agent Flows for Social Media Analysis

Social media platforms generate volumes of heterogeneous data, capturing user behaviors, textual content, and network structures. Analyzing such data is crucial for understanding phenomena such as opinion dynamics, community formation, and information diffusion. However, discovering insights from this complex landscape is exploratory, conceptually challenging, and requires expertise in social media mining and visualization. Existing automated approaches, including large language models (LLMs), remain largely confined to structured tabular data and cannot adequately address the heterogeneity of social media analysis. We present SIA (Social Insight Agents), an LLM agent system that links heterogeneous multi-modal data, including raw inputs (e.g., text, network, and behavioral data), mined analytical results, and rendered visual artifacts, through coordinated agent flows. Guided by an insight-oriented taxonomy connecting insight types with suitable mining methods and visualization strategies, SIA adopts a stage-synchronized strategy that proceeds through goal decomposition, query, mining, visualization, and reporting stages. At each stage, it collects prior information to jointly plan and execute agent actions, while the coordinator maintains cross-stage action dependencies and assembles and distributes data to agents. Through quantitative evaluation and case studies supported by an interactive interface, we show that SIA can discover diverse and meaningful insights from social media with opportunities for subsequent reliability assessment.

cs.HC↗

arXiv2025

NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models

Jailbreak attacks bypass the safety alignment of large language models (LLMs) to elicit harmful outputs, yet the vast parameter space makes diagnosing the underlying failure mechanisms extremely challenging. We present NeuroBreak, a visual analytics system that helps experts progressively unpack jailbreak mechanisms from layer-level semantics down to neuron-level behaviors. A layer-wise probing pipeline traces how harmful representations evolve across layers, while a dual-dimensional character--behavior categorization reveals each safety-related neuron's inherent tendency and contextual contribution. These analyses are made interpretable through tailored visualization designs: a task-driven probing projection that reveals safety decision boundaries, a dual-stream semantic evolution flow that traces cross-layer semantic shifts, and a character--behavior chord graph that unifies neuron roles, attribution scores, and collaborative relations in a single view with in-situ causal verification. Quantitative evaluations and case studies show that NeuroBreak uncovers safety failure causes and provides actionable insights for strengthening LLM defenses.

cs.CR↗

arXiv2025

ProTAL: A Drag-and-Link Video Programming Framework for Temporal Action Localization

Temporal Action Localization (TAL) aims to detect the start and end timestamps of actions in a video. However, the training of TAL models requires a substantial amount of manually annotated data. Data programming is an efficient method to create training labels with a series of human-defined labeling functions. However, its application in TAL faces difficulties of defining complex actions in the context of temporal video frames. In this paper, we propose ProTAL, a drag-and-link video programming framework for TAL. ProTAL enables users to define \textbf{key events} by dragging nodes representing body parts and objects and linking them to constrain the relations (direction, distance, etc.). These definitions are used to generate action labels for large-scale unlabelled videos. A semi-supervised method is then employed to train TAL models with such labels. We demonstrate the effectiveness of ProTAL through a usage scenario and a user study, providing insights into designing video programming framework.

cs.HC↗

arXiv2025

ReSpark: Leveraging Previous Data Reports as References to Generate New Reports with LLMs

Creating data reports is a labor-intensive task involving iterative data exploration, insight extraction, and narrative construction. A key challenge lies in composing the analysis logic-from defining objectives and transforming data to identifying and communicating insights. Manually crafting this logic can be cognitively demanding. While experienced analysts often reuse scripts from past projects, finding a perfect match for a new dataset is rare. Even when similar analyses are available online, they usually share only results or visualizations, not the underlying code, making reuse difficult. To address this, we present ReSpark, a system that leverages large language models (LLMs) to reverse-engineer analysis logic from existing reports and adapt it to new datasets. By generating draft analysis steps, ReSpark provides a warm start for users. It also supports interactive refinement, allowing users to inspect intermediate outputs, insert objectives, and revise content. We evaluate ReSpark through comparative and user studies, demonstrating its effectiveness in lowering the barrier to generating data reports without relying on existing analysis code.

cs.HC↗

arXiv2025

NoteFlow: Leveraging Charts as Sight Glasses for Consistent and Continuous Data Flow Tracing

Computational notebooks offer a flexible environment for exploratory data analysis (EDA), but this flexibility often leads to disorganized and iterative execution of notebook cells, making it difficult to track how data states evolve. Consequently, data scientists must devote extra mental effort to staying aware of data states, which is both tedious and prone to overlooking anomalies. To address this challenge, we developed NoteFlow, a notebook extension that leverages charts as ``sight glasses'' to provide a consistent and continuous tracing of data flow. NoteFlow allows users to (1) validate various facets of the current data state using recommended charts provided immediately after each cell execution, and (2) trace the global evolution of selected charts to continuously observe how particular data attributes evolve throughout the EDA process. We evaluated NoteFlow's effectiveness through a controlled study with 12 participants and a one-month field study with 2 data scientists on real-world workflows.

cs.HC↗

arXiv2024

ViSTec: Video Modeling for Sports Technique Recognition and Tactical Analysis

The immense popularity of racket sports has fueled substantial demand in tactical analysis with broadcast videos. However, existing manual methods require laborious annotation, and recent attempts leveraging video perception models are limited to low-level annotations like ball trajectories, overlooking tactics that necessitate an understanding of stroke techniques. State-of-the-art action segmentation models also struggle with technique recognition due to frequent occlusions and motion-induced blurring in racket sports videos. To address these challenges, We propose ViSTec, a Video-based Sports Technique recognition model inspired by human cognition that synergizes sparse visual data with rich contextual insights. Our approach integrates a graph to explicitly model strategic knowledge in stroke sequences and enhance technique recognition with contextual inductive bias. A two-stage action perception model is jointly trained to align with the contextual knowledge in the graph. Experiments demonstrate that our method outperforms existing models by a significant margin. Case studies with experts from the Chinese national table tennis team validate our model's capacity to automate analysis for technical actions and tactical strategies. More details are available at: https://ViSTec2024.github.io/.

cs.CV↗

arXiv2024

VAID: Indexing View Designs in Visual Analytics System

Visual analytics (VA) systems have been widely used in various application domains. However, VA systems are complex in design, which imposes a serious problem: although the academic community constantly designs and implements new designs, the designs are difficult to query, understand, and refer to by subsequent designers. To mark a major step forward in tackling this problem, we index VA designs in an expressive and accessible way, transforming the designs into a structured format. We first conducted a workshop study with VA designers to learn user requirements for understanding and retrieving professional designs in VA systems. Thereafter, we came up with an index structure VAID to describe advanced and composited visualization designs with comprehensive labels about their analytical tasks and visual designs. The usefulness of VAID was validated through user studies. Our work opens new perspectives for enhancing the accessibility and reusability of professional visualization designs.

cs.HC↗

arXiv2023

ChartGPT: Leveraging LLMs to Generate Charts from Abstract Natural Language

The use of natural language interfaces (NLIs) to create charts is becoming increasingly popular due to the intuitiveness of natural language interactions. One key challenge in this approach is to accurately capture user intents and transform them to proper chart specifications. This obstructs the wide use of NLI in chart generation, as users' natural language inputs are generally abstract (i.e., ambiguous or under-specified), without a clear specification of visual encodings. Recently, pre-trained large language models (LLMs) have exhibited superior performance in understanding and generating natural language, demonstrating great potential for downstream tasks. Inspired by this major trend, we propose ChartGPT, generating charts from abstract natural language inputs. However, LLMs are struggling to address complex logic problems. To enable the model to accurately specify the complex parameters and perform operations in chart generation, we decompose the generation process into a step-by-step reasoning pipeline, so that the model only needs to reason a single and specific sub-task during each run. Moreover, LLMs are pre-trained on general datasets, which might be biased for the task of chart generation. To provide adequate visualization knowledge, we create a dataset consisting of abstract utterances and charts and improve model performance through fine-tuning. We further design an interactive interface for ChartGPT that allows users to check and modify the intermediate outputs of each step. The effectiveness of the proposed system is evaluated through quantitative evaluations and a user study.

cs.HC↗