VizAbility: Enhancing Chart Accessibility with LLM-based Conversational Interaction
Joshua Gorniak, Yoon Kim, Donglai Wei, Nam Wook Kim
摘要
Question: Your question "Where am I ?" was categorized as being related to structure, and as such has been answered based on the treeview.
Answer: Current Position: 2 of 2. Temporal Polarity equals positive. 71 values. Press t to open table.
navigating the chart Question: Your question "How do I get to the x axis?" was categorized as being related to structure, and as such has been answered based on the treeview.
Answer: Press the up arrow key. Press the left arrow key. navigating the chart Question: Your question "What is the overall trend of this chart?" was categorized as being , and as such, has been answered based on the data in the chart.
Answer: The overall trend in Temperature Anomaly (°C) from 1850 to 2021, according to the bar chart data, shows a mean temperature anomaly of 0.042°C, with a wide range of anomalies from -0.43°C to 1.03°C. data-driven Question: Your question "Are there more blue bars or red bars?" was categorized as being , and as such, has been answered based on the data in the chart.
Answer: There are more years represented by negative Temperature Anomaly (Blue Bars) than positive Temperature Anomaly (Red Bars).
data-driven Question: Your question "What does it mean by temperature anomaly?" was categorized as being , and as such, has been answered based on information found on the web.
Answer: In the context of this dataset, "Temperature Anomaly" represents the deviation of the yearly temperature from the long-term average temperature. [...] context-seeking Figure 1: VizAbility's overall user interface presents the keyboard navigation of chart content or data tables augmented with the ability to ask natural language questions. Example queries are shown on the right side, including visual & data queries, navigation, and context-seeking questions.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper4
- "Mango Mango, How to Let The Lettuce Dry Without A Spinner?": Exploring User Perceptions of Using An LLM-Based Conversational Assistant Toward Cooking PartnerSzeyi Chan, Jiachen Li, Bingsheng Yao, Amama Mahmood 等CSCW 2025 · 被引用 4 次
- Improving Low-Vision Chart Accessibility via On-Cursor Visual ContextYotam Sechayk, Hennes Rave, Max Rädler, Mark Colley 等CHI 2026 · 被引用 1 次
- Lost in Instructions: Study of Blind Users' Experiences with DIY Manuals and AI-Rewritten Instructions for Assembly, Operation, and Troubleshooting of Tangible ProductsMonalika Padma Reddy, Aruna Balasubramanian, Jiawei Zhou, Xiaojun Bi 等CHI 2026 · 被引用 1 次
- GeoVisA11y: An AI-based Geovisualization Question-Answering System for Screen-Reader UsersChu Li, Rock Yuren Pang, Arnavi Chheda-Kothary, Ather Sharif 等CHI 2026 · 被引用 1 次
它引用的顶会 Paper17
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma 等NeurIPS 2022 · 被引用 22,562 次
- Unifying Vision-and-Language Tasks via Text GenerationJaemin Cho, Jie Lei, Hao Tan, Mohit BansalICML 2021 · 被引用 624 次
- G-Eval: NLG Evaluation using Gpt-4 with Better Human AlignmentYang Liu, Dan Iter, Yichong Xu, Shuohang Wang 等EMNLP 2023 · 被引用 549 次
- In-Context Impersonation Reveals Large Language Models' Strengths and BiasesLeonard Salewski, Stephan Alaniz, Isabel Rio-Torto, Eric Schulz 等NeurIPS 2023 · 被引用 259 次
- Can Large Language Models Be an Alternative to Human Evaluations?David Cheng-Han Chiang, Hung-yi LeeACL 2023 · 被引用 254 次
相关 Paper
- Visualizing Tree-of-Analysis: Facilitating Conversational Visual Analytics for NovicesFeiyuan Qu, Tan Tang, Zeyang Fu, Yan Chen 等CHI 2026 · 被引用 1 次
- SimpleNet: A Simple Network for Image Anomaly Detection and LocalizationZhikang Liu, Yiming Zhou, Yuansheng Xu, Zilei WangCVPR 2023
- Exploring Chart Question Answering for Blind and Low Vision UsersJiho Kim, Arjun Srinivasan, Nam Wook Kim, Yea-Seul KimCHI 2023 · 被引用 33 次
- ClimateViz: A Benchmark for Statistical Reasoning and Fact Verification on Scientific ChartsRuiran Su, Jiasheng Si, Zhijiang Guo, Janet B. PierrehumbertEMNLP 2025
- EncQA: Benchmarking Vision-Language Models on Visual Encodings for ChartsKushin Mukherjee, Donghao Ren, Dominik Moritz, Yannick AssogbaIEEE VIS 2025 · 被引用 3 次
