# nvBench 2.0: Resolving Ambiguity in Text-to-Visualization through Stepwise Reasoning

arXiv: https://arxiv.org/abs/2503.12880 · HTML: https://mlsanity.com/paper/2503.12880/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 15 of its 74 references that are in the map.
- First posted on arXiv 17 Mar 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 15 of 15)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs](https://mlsanity.com/paper/2406.18629/) (2024)
- [Not Enough Data? Deep Learning to the Rescue!](https://mlsanity.com/paper/1911.03118/) (2019)
- [Text2Analysis: A Benchmark of Table Question Answering with Advanced Data Analysis and Unclear Queries](https://mlsanity.com/paper/2312.13671/) (2023)
- [AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries](https://mlsanity.com/paper/2406.19073/) (2024)
- [Weakly Supervised Data Augmentation Through Prompting for Dialogue Understanding](https://mlsanity.com/paper/2210.14169/) (2022)
- [SynthBio: A Case Study in Human-AI Collaborative Curation of Text Datasets](https://mlsanity.com/paper/2111.06467/) (2021)
- [Prompt4Vis: Prompting Large Language Models with Example Mining and Schema Filtering for Tabular Data Visualization](https://mlsanity.com/paper/2402.07909/) (2024)
- [Quda: Natural Language Queries for Visual Data Analytics](https://mlsanity.com/paper/2005.03257/) (2020)
- [Marrying Dialogue Systems with Data Visualization: Interactive Data Visualization Generation from Natural Language Conversations](https://mlsanity.com/paper/2307.16013/) (2023)
- [A Plug-and-Play Natural Language Rewriter for Natural Language to SQL](https://mlsanity.com/paper/2412.17068/) (2024)
- [Generating Analytic Specifications for Data Visualization from Natural Language Queries using Large Language Models](https://mlsanity.com/paper/2408.13391/) (2024)

## Built on by (most cited first, 19 of 19)

- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [A Survey of Data Agents: Emerging Paradigm or Overstated Hype?](https://mlsanity.com/paper/2510.23587/) (2025)
- [Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking](https://mlsanity.com/paper/2505.11065/) (2025)
- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [DeepVIS: Bridging Natural Language and Data Visualization Through Step-wise Reasoning](https://mlsanity.com/paper/2508.01700/) (2025)
- [VisCoder2: Building Multi-Language Visualization Coding Agents](https://mlsanity.com/paper/2510.23642/) (2025)
- [Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence](https://mlsanity.com/paper/2606.15932/) (2026)
- [Exploring Multimodal Prompt for Visualization Authoring with Large Language Models](https://mlsanity.com/paper/2504.13700/) (2025)
- [RealChart2Code: Advancing Chart-to-Code Generation with Real Data and Multi-Task Evaluation](https://mlsanity.com/paper/2603.25804/) (2026)
- [OmniDiagram: Advancing Unified Diagram Code Generation via Visual Interrogation Reward](https://mlsanity.com/paper/2604.05514/) (2026)
- [CLARITY: A Framework and Benchmark for Conversational Language Ambiguity and Unanswerability in Interactive NL2SQL Systems](https://mlsanity.com/paper/2604.22313/) (2026)
- [DataMagic: Transforming Tabular Data into Data Insight Video](https://mlsanity.com/paper/2606.20388/) (2026)
- [DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios](https://mlsanity.com/paper/2604.25914/) (2026)
- [SQLConductor: Search-to-Policy Learning for Step-wise Text-to-SQL Orchestration](https://mlsanity.com/paper/2606.23537/) (2026)
- [Business Utility of Large Language Models as Exploratory Data Analysis Agents](https://mlsanity.com/paper/2606.00051/) (2026)
- [ChartAnno: Benchmarking Multimodal Large Language Models for Chart Annotation Generation](https://mlsanity.com/paper/2608.03464/) (2026)
- [DashArena: Benchmarking LLMs on Interactive Analytic Dashboard Generation](https://mlsanity.com/paper/2608.10567/) (2026)
- [Data Agents: Agentic Data Systems](https://mlsanity.com/paper/2609.24137/) (2026)
- [DataVista: Diagnosing Multimodal LLMs on Data Video Understanding](https://mlsanity.com/paper/2610.11993/) (2026)

## Abstract (arXiv)

Text-to-Visualization (Text2VIS) enables users to create visualizations from natural language queries, making data insights more accessible. However, Text2VIS faces challenges in interpreting ambiguous queries, as users often express their visualization needs in imprecise language. To address this challenge, we introduce nBench 2.0, a new benchmark designed to evaluate Text2VIS systems in scenarios involving ambiguous queries. nvBench 2.0 includes 7,878 natural language queries and 24,076 corresponding visualizations, derived from 780 tables across 153 domains. It is built using a controlled ambiguity-injection pipeline that generates ambiguous queries through a reverse-generation workflow. By starting with unambiguous seed visualizations and selectively injecting ambiguities, the pipeline yields multiple valid interpretations for each query, with each ambiguous query traceable to its corresponding visualization through step-wise reasoning paths. We evaluate various Large Language Models (LLMs) on their ability to perform ambiguous Text2VIS tasks using nBench 2.0. We also propose Step-Text2Vis, an LLM-based model trained on nvBench 2.0, which enhances performance in ambiguous scenarios through step-wise preference optimization. Our results show that Step-Text2Vis outperforms all baselines, setting a new state-of-the-art for ambiguous Text2VIS tasks. Our source code and data are available at https://nvbench2.github.io/