# VOICE: Visual Oracle for Interaction, Conversation, and Explanation

arXiv: https://arxiv.org/abs/2304.04083 · HTML: https://mlsanity.com/paper/2304.04083/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Apr 2023.

## Built on by (most cited first, 7 of 7)

- [A Survey of Data Agents: Emerging Paradigm or Overstated Hype?](https://mlsanity.com/paper/2510.23587/) (2025)
- [NLI4VolVis: Natural Language Interaction for Volume Visualization via LLM Multi-Agents and Editable 3D Gaussian Splatting](https://mlsanity.com/paper/2507.12621/) (2025)
- [SciVisAgentBench: A Benchmark for Evaluating Scientific Data Analysis and Visualization Agents](https://mlsanity.com/paper/2603.29139/) (2026)
- [Augmenting a Large Language Model with a Combination of Text and Visual Data for Conversational Visualization of Global Geospatial Data](https://mlsanity.com/paper/2501.09521/) (2025)
- [AIvaluateXR: An Evaluation Framework for on-Device AI in XR with Benchmarking Results](https://mlsanity.com/paper/2502.15761/) (2025)
- [SciVisAgentSkills: Design and Evaluation of Agent Skills for Scientific Data Analysis and Visualization](https://mlsanity.com/paper/2606.05525/) (2026)
- [VoCa: Designing Speech-Canvas Interaction for Voice-Based Conversational Agents](https://mlsanity.com/paper/2610.04706/) (2026)

## Abstract (arXiv)

We present VOICE, a novel approach to science communication that connects large language models' (LLM) conversational capabilities with interactive exploratory visualization. VOICE introduces several innovative technical contributions that drive our conversational visualization framework. Our foundation is a pack-of-bots that can perform specific tasks, such as assigning tasks, extracting instructions, and generating coherent content. We employ fine-tuning and prompt engineering techniques to tailor bots' performance to their specific roles and accurately respond to user queries. Our interactive text-to-visualization method generates a flythrough sequence matching the content explanation. Besides, natural language interaction provides capabilities to navigate and manipulate the 3D models in real-time. The VOICE framework can receive arbitrary voice commands from the user and respond verbally, tightly coupled with corresponding visual representation with low latency and high accuracy. We demonstrate the effectiveness of our approach by applying it to the molecular visualization domain: analyzing three 3D molecular models with multi-scale and multi-instance attributes. We finally evaluate VOICE with the identified educational experts to show the potential of our approach. All supplemental materials are available at https://osf.io/g7fbr.