VizAbility: Enhancing Chart Accessibility with LLM-based Conversational Interaction
Joshua Gorniak, Yoon Kim, Donglai Wei, Nam Wook Kim
Abstract
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.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 9f9aad85-ee2a-400c-8dd4-8244f98c3507Cited by top-tier papers4
- "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 et al.CSCW 2025 · 4 citations
- Improving Low-Vision Chart Accessibility via On-Cursor Visual ContextYotam Sechayk, Hennes Rave, Max Rädler, Mark Colley et al.CHI 2026 · 1 citation
- 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 et al.CHI 2026 · 1 citation
- GeoVisA11y: An AI-based Geovisualization Question-Answering System for Screen-Reader UsersChu Li, Rock Yuren Pang, Arnavi Chheda-Kothary, Ather Sharif et al.CHI 2026 · 1 citation
Builds on17
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- Unifying Vision-and-Language Tasks via Text GenerationJaemin Cho, Jie Lei, Hao Tan, Mohit BansalICML 2021 · 624 citations
- G-Eval: NLG Evaluation using Gpt-4 with Better Human AlignmentYang Liu, Dan Iter, Yichong Xu, Shuohang Wang et al.EMNLP 2023 · 549 citations
- In-Context Impersonation Reveals Large Language Models' Strengths and BiasesLeonard Salewski, Stephan Alaniz, Isabel Rio-Torto, Eric Schulz et al.NeurIPS 2023 · 259 citations
- Can Large Language Models Be an Alternative to Human Evaluations?David Cheng-Han Chiang, Hung-yi LeeACL 2023 · 254 citations
Related papers
- Visualizing Tree-of-Analysis: Facilitating Conversational Visual Analytics for NovicesFeiyuan Qu, Tan Tang, Zeyang Fu, Yan Chen et al.CHI 2026 · 1 citation
- 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 · 33 citations
- 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 · 3 citations
