pith. sign in

arxiv: 2509.19182 · v2 · pith:HW7VCTOPnew · submitted 2025-09-23 · 💻 cs.HC · cs.AI

YAC: Bridging Natural Language and Interactive Visual Exploration with Generative AI for Biomedical Data Discovery

Devin Lange , Shanghua Gao , Pengwei Sui , Priya Misner , Astrid van den Brandt , Austen Money , Nikolay Akhmetov , Lisa Choy
show 2 more authors
Marinka Zitnik Nils Gehlenborg
This is my paper

Pith reviewed 2026-05-21 22:07 UTC · model grok-4.3

classification 💻 cs.HC cs.AI
keywords natural language interfacesinteractive visualizationsgenerative AIbiomedical data discoverymulti-agent systemsdata explorationhuman-computer interactionadjustment widgets
0
0 comments X

The pith

YAC turns natural language queries into adjustable, linked interactive visualizations for biomedical data exploration.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces YAC as a prototype that merges conversational natural language input with visual data tools for discovering patterns in biomedical datasets. It relies on a multi-agent AI architecture that converts user questions into declarative instructions for building connected charts, applying filters, and generating explanatory text. Direct adjustment widgets let users tweak the AI's structured output on the fly, while the system also flags its own limits and links back to live data elements. A user study with domain experts helped reveal practical strengths and gaps in this hybrid interface. The work shows how generative AI can support fluid switching between asking questions and manipulating visuals without losing user control.

Core claim

YAC shows that a tool-calling multi-agent system can produce declarative output interpreted to render linked interactive visualizations, apply data filters, generate clarifying structured text, and support direct adjustment widgets that let users modify the generated structures for biomedical data discovery.

What carries the argument

A tool-calling multi-agent system that generates declarative output interpreted to render visualizations and apply filters.

If this is right

  • Users gain the ability to start with open-ended questions and then refine results through both visual interaction and direct edits to the underlying structure.
  • Clarifying text output helps users understand system boundaries and data meanings without leaving the exploration flow.
  • Linked visualizations update together when filters or adjustments are applied, preserving context across multiple views.
  • The design supports both initial discovery and iterative correction within the same interface.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Similar agent-driven declarative layers could be tested in non-biomedical domains such as environmental sensor data or financial time series.
  • Future versions might incorporate live data streams to see whether the same declarative generation remains stable under continuous updates.
  • Combining this approach with collaborative multi-user sessions could reveal how shared adjustments affect group interpretation of the same dataset.

Load-bearing premise

The multi-agent pipeline will consistently translate user intent into accurate visualization actions and filters that adjustment widgets can readily correct when errors occur.

What would settle it

Observing sessions where most user queries produce persistent mis-mapped filters or visualizations that the adjustment widgets do not resolve within a few clicks, resulting in repeated restarts or abandoned explorations.

Figures

Figures reproduced from arXiv: 2509.19182 by Astrid van den Brandt, Austen Money, Devin Lange, Lisa Choy, Marinka Zitnik, Nikolay Akhmetov, Nils Gehlenborg, Pengwei Sui, Priya Misner, Shanghua Gao.

Figure 1
Figure 1. Figure 1: The YAC discovery interface contains two general sections. (a) The chat interface displays user [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: When a user submits a query (a), it is sent to a multi-agent system (b). This system consists of an [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Structure of the visualization grammar. (a) A specification contains at least a data source section, which [PITH_FULL_IMAGE:figures/full_fig_p007_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: YAC includes several types of adjustment widgets. For example: point filters (a) and interval filters (b) [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: The visualization grammar supports linking across specifications and entities. (a) Point selections [PITH_FULL_IMAGE:figures/full_fig_p010_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Four snapshots from the Palmer Penguins usage scenario. (a) User has selected penguins with a [PITH_FULL_IMAGE:figures/full_fig_p012_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Four snapshots from the NIH 4D Nucleome Data Portal usage scenario. (a) The user requests the [PITH_FULL_IMAGE:figures/full_fig_p013_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Four snapshots from the NIH Cellular Senescence Network Data Portal usage scenario. [PITH_FULL_IMAGE:figures/full_fig_p014_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Four snapshots from the NIH Human BioMolecular Atlas Program Data Portal usage scenario. (a) [PITH_FULL_IMAGE:figures/full_fig_p015_9.png] view at source ↗
read the original abstract

Incorporating natural language input has the potential to improve the capabilities of biomedical data discovery interfaces. However, user interface elements and visualizations are still powerful tools for interacting with data. In our prototype system, YAC, Yet Another Chatbot, we integrate natural language and interactive visualizations. YAC uses a tool-calling multi-agent system to generate declarative output, which is interpreted to render linked interactive visualizations and apply data filters. We also include adjustment widgets, which allow users to directly modify the structured output. Structured text is also generated to clarify user intent, notify users of system boundaries, and explain aspects of the data with live data element links. We conducted a user study with domain experts to surface areas where YAC can be improved. Furthermore we reflect on the capabilities and design of this system with an analysis of its technical dimensions.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 2 minor

Summary. The manuscript presents YAC ('Yet Another Chatbot'), a prototype system for biomedical data discovery that integrates natural language input with interactive visualizations. It employs a tool-calling multi-agent architecture to generate declarative output interpreted for rendering linked visualizations, applying filters, and enabling direct adjustments via widgets, while also producing structured clarifying text. The authors report conducting a user study with domain experts to identify improvement areas and provide a reflective analysis of the system's technical dimensions.

Significance. If the described integration of the multi-agent pipeline with declarative outputs and correction widgets proves reliable, the work could contribute to hybrid conversational-visual interfaces in biomedical HCI. The prototype nature, inclusion of adjustment mechanisms, and expert user study offer practical design insights. However, the absence of quantitative evaluation limits demonstrated effectiveness, making the significance prospective rather than established.

major comments (1)
  1. User Study section: The manuscript states that a user study with domain experts was conducted to surface improvement areas, but reports no quantitative results, task metrics, error rates, misinterpretation frequencies, or baseline comparisons. This is load-bearing for the central claim of effective integration, as it leaves the reliability of the tool-calling pipeline in mapping intent to declarative visualization actions and filters supported only by qualitative reflection.
minor comments (2)
  1. Abstract: The abstract could more clearly summarize the key outcomes or limitations identified in the user study and technical analysis to better convey the paper's contributions beyond system description.
  2. System description: The high-level overview of the multi-agent tool-calling and declarative output interpretation would benefit from additional concrete examples of query-to-visualization mappings or failure modes to aid reproducibility.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their constructive review of our manuscript on the YAC prototype. We address the major comment below by clarifying the qualitative scope of the user study and the manuscript's positioning as a design-oriented prototype rather than a quantitative evaluation.

read point-by-point responses

  1. Referee: [—] User Study section: The manuscript states that a user study with domain experts was conducted to surface improvement areas, but reports no quantitative results, task metrics, error rates, misinterpretation frequencies, or baseline comparisons. This is load-bearing for the central claim of effective integration, as it leaves the reliability of the tool-calling pipeline in mapping intent to declarative visualization actions and filters supported only by qualitative reflection.

    Authors: We acknowledge that the reported user study contains no quantitative metrics, task performance data, error rates, or baseline comparisons. This is by design: the study was conducted as a small-scale qualitative exploration with domain experts specifically to identify improvement opportunities and to inform our reflective analysis of the system's technical dimensions, rather than to statistically validate the reliability or effectiveness of the multi-agent pipeline. The manuscript's abstract and introduction frame the contribution as the description of a prototype architecture that integrates natural language with interactive visualizations via declarative outputs and adjustment widgets, together with expert-informed reflections on its capabilities and limitations. We do not advance a central claim of proven effectiveness or quantitative reliability for the tool-calling mechanism. To address the referee's concern, we will revise the User Study section, the abstract, and the introduction to explicitly state the qualitative purpose of the study and to temper any implication of demonstrated integration reliability, making the scope of the evaluation clearer to readers. revision: partial

Circularity Check

0 steps flagged

No significant circularity

full rationale

The manuscript is a system-description and user-study paper presenting the YAC prototype architecture (multi-agent tool-calling pipeline, declarative output interpretation, adjustment widgets, and structured text generation). No equations, fitted parameters, uniqueness theorems, or derivation steps appear in the provided text or abstract. The central claims rest on architectural choices and qualitative reflections from the user study rather than any self-referential reduction or self-citation load-bearing argument. The work is therefore self-contained against external benchmarks with no circular steps to isolate.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No mathematical model or derivation is present; the work rests on standard assumptions about multi-agent LLM reliability and the utility of declarative visualization specifications.

pith-pipeline@v0.9.0 · 5707 in / 1074 out tokens · 22453 ms · 2026-05-21T22:07:41.342002+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Raiven: LLM-Based Visualization Authoring via Domain-Specific Language Mediation

    cs.HC 2026-04 unverdicted novelty 7.0

    Raiven mediates LLM visualization authoring via a formally defined DSL that unifies scientific and information visualization, producing deterministic, verifiable code from metadata-only inputs.

  2. Figures as Interfaces: Toward LLM-Native Artifacts for Scientific Discovery

    cs.HC 2026-04 unverdicted novelty 7.0

    LLM-native figures embed provenance and enable direct LLM interaction with scientific visualizations to accelerate discovery and improve reproducibility.

Reference graph

Works this paper leans on

57 extracted references · 57 canonical work pages · cited by 2 Pith papers · 3 internal anchors

  1. [1]

    Charbonneau, Arthur Brady, Karl Czajkowski, Jain Aluvathingal, Saranya Canchi, Robert Carter, Kyle Chard, Daniel J

    Amanda L. Charbonneau, Arthur Brady, Karl Czajkowski, Jain Aluvathingal, Saranya Canchi, Robert Carter, Kyle Chard, Daniel J. B. Clarke, Jonathan Crabtree, Heather H. Creasy, Mike D’Arcy, Victor Felix, Michelle Giglio, Alicia Gingrich, Rayna M. Harris, Theresa K. Hodges, Olukemi Ifeonu, Minji Jeon, Eryk Kropiwnicki, Marisa C. W. Lim, R. Lee Liming, Jessic...

    work page doi:10.1093/gigascience/giac105 2022

  2. [2]

    Juntong Chen, Jiang Wu, Jiajing Guo, Vikram Mohanty, Xueming Li, Jorge Piazentin Ono, Wenbin He, Liu Ren, and Dongyu Liu. 2025. InterChat: Enhancing Generative Visual Analytics Using Multimodal Interactions.Computer Graphics Forum44, 3 (2025), e70112. doi:10.1111/cgf.70112

    work page doi:10.1111/cgf.70112 2025

  3. [3]

    Nan Chen, Yuge Zhang, Jiahang Xu, Kan Ren, and Yuqing Yang. 2025. VisEval: A Benchmark for Data Visualization in the Era of Large Language Models.IEEE Transactions on Visualization and Computer Graphics31, 1 (Jan. 2025), 1301–1311. doi:10.1109/TVCG.2024.3456320

    work page doi:10.1109/tvcg.2024.3456320 2025

  4. [4]

    Weiwei Cui, Xiaoyu Zhang, Yun Wang, He Huang, Bei Chen, Lei Fang, Haidong Zhang, Jian-Guan Lou, and Dongmei Zhang. 2020. Text-to-Viz: Automatic Generation of Infographics from Proportion-Related Natural Language Statements. IEEE Transactions on Visualization and Computer Graphics26, 1 (Jan. 2020), 906–916. doi:10.1109/TVCG.2019.2934785

    work page doi:10.1109/tvcg.2019.2934785 2020

  5. [5]

    Ge, Yiren Ding, Lane Harrison, Fumeng Yang, and Matthew Kay

    Yuan Cui, Lily W. Ge, Yiren Ding, Lane Harrison, Fumeng Yang, and Matthew Kay. 2025. Promises and Pitfalls: Using Large Language Models to Generate Visualization Items.IEEE Transactions on Visualization and Computer Graphics31, 1 (Jan. 2025), 1094–1104. doi:10.1109/TVCG.2024.3456309

    work page doi:10.1109/tvcg.2024.3456309 2025

  6. [7]

    Belmont, Mitchell Guttman, Victor O

    Job Dekker, Andrew S. Belmont, Mitchell Guttman, Victor O. Leshyk, John T. Lis, Stavros Lomvardas, Leonid A. Mirny, Clodagh C. O’Shea, Peter J. Park, Bing Ren, Joan C. Ritland Politz, Jay Shendure, and Sheng Zhong. 2017. The 4D Nucleome Project.Nature549, 7671 (Sept. 2017), 219–226. doi:10.1038/nature23884

    work page doi:10.1038/nature23884 2017

  7. [8]

    Victor Dibia. 2023. LIDA: A Tool for Automatic Generation of Grammar-Agnostic Visualizations and Infographics Using Large Language Models. InProceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), Danushka Bollegala, Ruihong Huang, and Alan Ritter (Eds.). Association for Computational Ling...

    work page doi:10.18653/v1/2023.acl-demo.11 2023

  8. [9]

    Victor Dibia and Çağatay Demiralp. 2018. Data2Vis: Automatic Generation of Data Visualizations Using Sequence to Sequence Recurrent Neural Networks. arXiv:1804.03126 [cs] doi:10.48550/arXiv.1804.03126

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.1804.03126 2018

  9. [10]

    Lin Gao, Jing Lu, Zekai Shao, Ziyue Lin, Shengbin Yue, Chiokit Leong, Yi Sun, Rory James Zauner, Zhongyu Wei, and Siming Chen. 2025. Fine-Tuned Large Language Model for Visualization System: A Study on Self-Regulated Learning in Education.IEEE Transactions on Visualization and Computer Graphics31, 1 (Jan. 2025), 514–524. doi:10.1109/TVCG. 2024.3456145

    work page doi:10.1109/tvcg 2025

  10. [11]

    Shanghua Gao, Richard Zhu, Zhenglun Kong, Ayush Noori, Xiaorui Su, Curtis Ginder, Theodoros Tsiligkaridis, and Marinka Zitnik. 2025. TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools. arXiv:2503.10970 [cs.AI] https://arxiv.org/abs/2503.10970

    work page arXiv 2025

  11. [12]

    Karahalios

    Tong Gao, Mira Dontcheva, Eytan Adar, Zhicheng Liu, and Karrie G. Karahalios. 2015. DataTone: Managing Ambiguity in Natural Language Interfaces for Data Visualization. InProceedings of the 28th Annual ACM Symposium on User Interface Software & Technology. ACM, Charlotte NC USA, 489–500. doi:10.1145/2807442.2807478

    work page doi:10.1145/2807442.2807478 2015

  12. [13]

    Gorman, Tony D

    Kristen B. Gorman, Tony D. Williams, and William R. Fraser. 2014. Ecological Sexual Dimorphism and Environmental Variability within a Community of Antarctic Penguins (Genus Pygoscelis).PLOS ONE9, 3 (March 2014), e90081. doi:10.1371/journal.pone.0090081

    work page doi:10.1371/journal.pone.0090081 2014

  13. [14]

    Jeffrey Heer and Dominik Moritz. 2024. Mosaic: An Architecture for Scalable & Interoperable Data Views.IEEE Transactions on Visualization and Computer Graphics30, 1 (Jan. 2024), 436–446. doi:10.1109/TVCG.2023.3327189

    work page doi:10.1109/tvcg.2023.3327189 2024

  14. [15]

    Enamul Hoque, Vidya Setlur, Melanie Tory, and Isaac Dykeman. 2018. Applying Pragmatics Principles for Interaction with Visual Analytics.IEEE Transactions on Visualization and Computer Graphics24, 1 (Jan. 2018), 309–318. doi:10. 1109/TVCG.2017.2744684

    work page arXiv 2018

  15. [16]

    Horst, Alison Presmanes Hill, and Kristen B

    Allison M. Horst, Alison Presmanes Hill, and Kristen B. Gorman. 2020. Allisonhorst/Palmerpenguins: V0.1.0. Zenodo. doi:10.5281/zenodo.3960218

    work page doi:10.5281/zenodo.3960218 2020

  16. [17]

    Jieying Huang, Yang Xi, Junnan Hu, and Jun Tao. 2023. FlowNL: Asking the Flow Data in Natural Languages.IEEE Transactions on Visualization and Computer Graphics29, 1 (Jan. 2023), 1200–1210. doi:10.1109/TVCG.2022.3209453 22 Lange et al

    work page doi:10.1109/tvcg.2022.3209453 2023

  17. [18]

    Zhaosong Huang, Ye Zhao, Wei Chen, Shengjie Gao, Kejie Yu, Weixia Xu, Mingjie Tang, Minfeng Zhu, and Mingliang Xu. 2020. A Natural-language-based Visual Query Approach of Uncertain Human Trajectories.IEEE Transactions on Visualization and Computer Graphics26, 1 (Jan. 2020), 1256–1266. doi:10.1109/TVCG.2019.2934671

    work page doi:10.1109/tvcg.2019.2934671 2020

  18. [19]

    Joel Jakubovic, Jonathan Edwards, and Tomas Petricek. 2023. Technical Dimensions of Programming Systems.The Art, Science, and Engineering of Programming7, 3 (2023), 13. doi:10.22152/programming-journal.org/2023/7/13

    work page doi:10.22152/programming-journal.org/2023/7/13 2023

  19. [20]

    Jaeyoung Kim, Sihyeon Lee, Hyeon Jeon, Keon-Joo Lee, Hee-Joon Bae, Bohyoung Kim, and Jinwook Seo. 2025. PhenoFlow: A Human-LLM Driven Visual Analytics System for Exploring Large and Complex Stroke Datasets.IEEE Transactions on Visualization and Computer Graphics31, 1 (Jan. 2025), 470–480. doi:10.1109/TVCG.2024.3456215

    work page doi:10.1109/tvcg.2024.3456215 2025

  20. [21]

    Efficient Memory Management for Large Language Model Serving with PagedAttention

    Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. Efficient Memory Management for Large Language Model Serving with PagedAttention. arXiv:2309.06180 [cs] doi:10.48550/arXiv.2309.06180

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2309.06180 2023

  21. [22]

    Devin Lange, Pengwei Sui, Shanghua Gao, Marinka Zitnik, and Nils Gehlenborg. 2025. DQVis Dataset: Natural Language to Biomedical Visualization

    work page 2025

  22. [23]

    Chunggi Lee, Tica Lin, Hanspeter Pfister, and Chen Zhu-Tian. 2025. Sportify: Question Answering with Embedded Visualizations and Personified Narratives for Sports Video.IEEE Transactions on Visualization and Computer Graphics 31, 1 (Jan. 2025), 12–22. doi:10.1109/TVCG.2024.3456332

    work page doi:10.1109/tvcg.2024.3456332 2025

  23. [24]

    Lee, Christopher C

    Patty J. Lee, Christopher C. Benz, Philip Blood, Katy Börner, Judith Campisi, Feng Chen, Heike Daldrup-Link, Phil De Jager, Li Ding, Francesca E. Duncan, Oliver Eickelberg, Rong Fan, Toren Finkel, David Furman, Vesna Garovic, Nils Gehlenborg, Carolyn Glass, Indra Heckenbach, Ziv-Bar Joseph, Pragati Katiyar, So-Jin Kim, Melanie Königshoff, George A. Kuchel...

    work page doi:10.1038/s43587-022-00326-5 2022

  24. [25]

    S. Liu, H. Miao, Z. Li, M. Olson, V. Pascucci, and P-T. Bremer. 2024. AVA: Towards Autonomous Visualization Agents through Visual Perception-Driven Decision-Making.Computer Graphics Forum43, 3 (2024), e15093. doi:10.1111/cgf. 15093

    work page doi:10.1111/cgf 2024

  25. [26]

    Ziao Liu, Xiao Xie, Moqi He, Wenshuo Zhao, Yihong Wu, Liqi Cheng, Hui Zhang, and Yingcai Wu. 2025. Smartboard: Visual Exploration of Team Tactics with LLM Agent.IEEE Transactions on Visualization and Computer Graphics31, 1 (Jan. 2025), 23–33. doi:10.1109/TVCG.2024.3456200

    work page doi:10.1109/tvcg.2024.3456200 2025

  26. [27]

    Yuyu Luo, Nan Tang, Guoliang Li, Chengliang Chai, Wenbo Li, and Xuedi Qin. 2021. Synthesizing Natural Language to Visualization (NL2VIS) Benchmarks from NL2SQL Benchmarks. InProceedings of the 2021 International Conference on Management of Data (SIGMOD ’21). Association for Computing Machinery, New York, NY, USA, 1235–1247. doi:10.1145/3448016.3457261

    work page doi:10.1145/3448016.3457261 2021

  27. [28]

    Yuyu Luo, Nan Tang, Guoliang Li, Jiawei Tang, Chengliang Chai, and Xuedi Qin. 2022. Natural Language to Visualization by Neural Machine Translation.IEEE Transactions on Visualization and Computer Graphics28, 1 (Jan. 2022), 217–226. doi:10.1109/TVCG.2021.3114848

    work page doi:10.1109/tvcg.2021.3114848 2022

  28. [29]

    Full-wave image reconstruction in transcranial photoacoustic computed tomography using a finite element method,

    Sehi L’Yi, Astrid van den Brandt, Etowah Adams, Huyen N. Nguyen, and Nils Gehlenborg. 2024. Learnable and Expressive Visualization Authoring through Blended Interfaces.IEEE Transactions on Visualization and Computer Graphics(2024). doi:10.1109/TVCG.2024.3456598

    work page doi:10.1109/tvcg.2024.3456598 2024

  29. [30]

    Jock Mackinlay, Pat Hanrahan, and Chris Stolte. 2007. Show Me: Automatic Presentation for Visual Analysis.IEEE Transactions on Visualization and Computer Graphics (InfoVis ’07)13, 6 (2007), 1137–1144. doi:10.1109/TVCG.2007.70594

    work page doi:10.1109/tvcg.2007.70594 2007

  30. [31]

    Stone, and Jeffrey Heer

    Andrew McNutt, Maureen C. Stone, and Jeffrey Heer. 2025. Mixing Linters with GUIs: A Color Palette Design Probe. IEEE Transactions on Visualization and Computer Graphics31, 1 (2025), 327–337. doi:10.1109/TVCG.2024.3456317

    work page doi:10.1109/tvcg.2024.3456317 2025

  31. [32]

    Arpit Narechania, Arjun Srinivasan, and John Stasko. 2021. NL4DV: A Toolkit for Generating Analytic Specifications for Data Visualization from Natural Language Queries.IEEE Transactions on Visualization and Computer Graphics27, 2 (Feb. 2021), 369–379. doi:10.1109/TVCG.2020.3030378

    work page doi:10.1109/tvcg.2020.3030378 2021

  32. [33]

    Borkin, and Nils Gehlenborg

    Aditeya Pandey, Sehi L’Yi, Qianwen Wang, Michelle A. Borkin, and Nils Gehlenborg. 2023. GenoREC: A Recommen- dation System for Interactive Genomics Data Visualization.IEEE Transactions on Visualization and Computer Graphics 29, 1 (Jan. 2023), 570–580. doi:10.1109/TVCG.2022.3209407

    work page doi:10.1109/tvcg.2022.3209407 2023

  33. [34]

    Rock Yuren Pang, Hope Schroeder, Kynnedy Simone Smith, Solon Barocas, Ziang Xiao, Emily Tseng, and Danielle Bragg. 2025. Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Review. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25). Association for Computing Mach...

    work page doi:10.1145/3706598.3713726 2025

  34. [35]

    Consciousness and cognition20(4), 1847–1854 (2011) https://doi.org/10.1016/j

    Ananda L. Roy, Richard S. Conroy, Veronica G. Taylor, Judy Mietz, Ian M. Fingerman, Michael J. Pazin, Phillip Smith, Carolyn M. Hutter, Dinah S. Singer, and Elizabeth L. Wilder. 2023. Elucidating the Structure and Function of the Nucleus—The NIH Common Fund 4D Nucleome Program.Molecular Cell83, 3 (Feb. 2023), 335–342. doi:10.1016/j. molcel.2022.12.025

    work page doi:10.1016/j 2023

  35. [36]

    Arvind Satyanarayan, Dominik Moritz, Kanit Wongsuphasawat, and Jeffrey Heer. 2017. Vega-Lite: A Grammar of Interactive Graphics.IEEE Transactions on Visualization and Computer Graphics23, 1 (Jan. 2017), 341–350. doi:10. 1109/TVCG.2016.2599030

    work page arXiv 2017

  36. [37]

    Arvind Satyanarayan, Ryan Russell, Jane Hoffswell, and Jeffrey Heer. 2016. Reactive Vega: A Streaming Dataflow Architecture for Declarative Interactive Visualization.IEEE Transactions on Visualization and Computer Graphics22, 1 (Jan. 2016), 659–668. doi:10.1109/TVCG.2015.2467091

    work page doi:10.1109/tvcg.2015.2467091 2016

  37. [38]

    Battersby, Melanie Tory, Rich Gossweiler, and Angel X

    Vidya Setlur, Sarah E. Battersby, Melanie Tory, Rich Gossweiler, and Angel X. Chang. 2016. Eviza: A Natural Language Interface for Visual Analysis. InProceedings of the 29th Annual Symposium on User Interface Software and Technology (UIST ’16). Association for Computing Machinery, New York, NY, USA, 365–377. doi:10.1145/2984511.2984588

    work page doi:10.1145/2984511.2984588 2016

  38. [39]

    Vidya Setlur and Arathi Kumar. 2020. Sentifiers: Interpreting Vague Intent Modifiers in Visual Analysis Using Word Co-occurrence and Sentiment Analysis. In2020 IEEE Visualization Conference (VIS). 216–220. doi:10.1109/VIS47514. 2020.00050

    work page doi:10.1109/vis47514 2020

  39. [40]

    Leixian Shen, Enya Shen, Yuyu Luo, Xiaocong Yang, Xuming Hu, Xiongshuai Zhang, Zhiwei Tai, and Jianmin Wang

    work page

  40. [41]

    doi:10.1109/TVCG.2022.3148007

    Towards Natural Language Interfaces for Data Visualization: A Survey.IEEE Transactions on Visualization and Computer Graphics29, 6 (June 2023), 3121–3144. doi:10.1109/TVCG.2022.3148007

    work page doi:10.1109/tvcg.2022.3148007 2023

  41. [42]

    Chuhan Shi, Weiwei Cui, Chengzhong Liu, Chengbo Zheng, Haidong Zhang, Qiong Luo, and Xiaojuan Ma. 2024. NL2Color: Refining Color Palettes for Charts with Natural Language.IEEE Transactions on Visualization and Computer Graphics30, 1 (Jan. 2024), 814–824. doi:10.1109/TVCG.2023.3326522

    work page doi:10.1109/tvcg.2023.3326522 2024

  42. [43]

    Michael P. Snyder, Shin Lin, Amanda Posgai, Mark Atkinson, Aviv Regev, Jennifer Rood, Orit Rozenblatt-Rosen, Leslie Gaffney, Anna Hupalowska, Rahul Satija, Nils Gehlenborg, Jay Shendure, Julia Laskin, Pehr Harbury, Nicholas A. Nystrom, Jonathan C. Silverstein, Ziv Bar-Joseph, Kun Zhang, Katy Börner, Yiing Lin, Richard Conroy, Dena Procaccini, Ananda L. Ro...

    work page

  43. [44]

    2019), 187–192

    The Human Body at Cellular Resolution: The NIH Human Biomolecular Atlas Program.Nature574, 7777 (Oct. 2019), 187–192. doi:10.1038/s41586-019-1629-x

    work page doi:10.1038/s41586-019-1629-x 2019

  44. [45]

    Glassman, Jeevana Priya Inala, and Chenglong Wang

    Priyan Vaithilingam, Elena L. Glassman, Jeevana Priya Inala, and Chenglong Wang. 2024. DynaVis: Dynamically Synthesized UI Widgets for Visualization Editing. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems (CHI ’24). Association for Computing Machinery, New York, NY, USA, 1–17. doi:10.1145/3613904. 3642639

    work page doi:10.1145/3613904 2024

  45. [46]

    Van Wijk

    J.J. Van Wijk. 2005. The Value of Visualization. InVIS 05. IEEE Visualization, 2005.IEEE, Minneapolis, MN, USA, 79–86. doi:10.1109/VISUAL.2005.1532781

    work page doi:10.1109/visual.2005.1532781 2005

  46. [47]

    Chenglong Wang, Bongshin Lee, Steven Drucker, Dan Marshall, and Jianfeng Gao. 2025. Data Formulator 2: Iterative Creation of Data Visualizations, with AI Transforming Data Along the Way. arXiv:2408.16119 [cs] doi:10.48550/arXiv. 2408.16119

    work page internal anchor Pith review doi:10.48550/arxiv 2025

  47. [48]

    Chenglong Wang, John Thompson, and Bongshin Lee. 2024. Data Formulator: AI-Powered Concept-Driven Vi- sualization Authoring.IEEE Transactions on Visualization and Computer Graphics30, 1 (Jan. 2024), 1128–1138. doi:10.1109/TVCG.2023.3326585

    work page doi:10.1109/tvcg.2023.3326585 2024

  48. [49]

    Huichen Will Wang, Mitchell Gordon, Leilani Battle, and Jeffrey Heer. 2025. DracoGPT: Extracting Visualization Design Preferences from Large Language Models.IEEE Transactions on Visualization and Computer Graphics31, 1 (Jan. 2025), 710–720. doi:10.1109/TVCG.2024.3456350

    work page doi:10.1109/tvcg.2024.3456350 2025

  49. [50]

    Yun Wang, Zhitao Hou, Leixian Shen, Tongshuang Wu, Jiaqi Wang, He Huang, Haidong Zhang, and Dongmei Zhang

    work page

  50. [51]

    doi:10.1109/TVCG.2022.3209357

    Towards Natural Language-Based Visualization Authoring.IEEE Transactions on Visualization and Computer Graphics(2022), 1–11. doi:10.1109/TVCG.2022.3209357

    work page doi:10.1109/tvcg.2022.3209357 2022

  51. [52]

    Zhen Wen, Luoxuan Weng, Yinghao Tang, Runjin Zhang, Yuxin Liu, Bo Pan, Minfeng Zhu, and Wei Chen. 2025. Exploring Multimodal Prompt for Visualization Authoring with Large Language Models. arXiv:2504.13700 doi:10. 48550/arXiv.2504.13700

    work page arXiv 2025

  52. [53]

    Kanit Wongsuphasawat, Dominik Moritz, Anushka Anand, Jock Mackinlay, Bill Howe, and Jeffrey Heer. 2016. Voyager: Exploratory Analysis via Faceted Browsing of Visualization Recommendations.IEEE Transactions on Visualization and Computer Graphics22, 1 (Jan. 2016), 649–658. doi:10.1109/TVCG.2015.2467191

    work page doi:10.1109/tvcg.2015.2467191 2016

  53. [54]

    Aoyu Wu, Yun Wang, Xinhuan Shu, Dominik Moritz, Weiwei Cui, Haidong Zhang, Dongmei Zhang, and Huamin Qu

    work page

  54. [55]

    Efficient optimization of cutoffs in quantum repeater chains,

    AI4VIS: Survey on Artificial Intelligence Approaches for Data Visualization.IEEE Transactions on Visualization and Computer Graphics28, 12 (Dec. 2022), 5049–5070. doi:10.1109/TVCG.2021.3099002

    work page doi:10.1109/tvcg.2021.3099002 2022

  55. [56]

    Youfu Yan, Yu Hou, Yongkang Xiao, Rui Zhang, and Qianwen Wang. 2025. KNOWNET: Guided Health Information Seeking from LLMs via Knowledge Graph Integration.IEEE Transactions on Visualization and Computer Graphics31, 1 (Jan. 2025), 547–557. doi:10.1109/TVCG.2024.3456364

    work page doi:10.1109/tvcg.2024.3456364 2025

  56. [57]

    Bowen Yu and Claudio T. Silva. 2020. FlowSense: A Natural Language Interface for Visual Data Exploration within a Dataflow System.IEEE Transactions on Visualization and Computer Graphics26, 1 (Jan. 2020), 1–11. arXiv:1908.00681 [cs] YAC: Bridging Natural Language and Interactive Visual Exploration with Generative AI for Biomedical Data Discovery25 doi:10....

    work page doi:10.1109/tvcg.2019.2934668 2020

  57. [58]

    Chen Zhu-Tian, Qisen Yang, Xiao Xie, Johanna Beyer, Haijun Xia, Yingcai Wu, and Hanspeter Pfister. 2023. Sporthesia: Augmenting Sports Videos Using Natural Language.IEEE Transactions on Visualization and Computer Graphics29, 1 (Jan. 2023), 918–928. doi:10.1109/TVCG.2022.3209497

    work page doi:10.1109/tvcg.2022.3209497 2023