# XNLI: Explaining and Diagnosing NLI-based Visual Data Analysis

arXiv: https://arxiv.org/abs/2301.10385 · HTML: https://mlsanity.com/paper/2301.10385/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 60 references that are in the map.
- First posted on arXiv 25 Jan 2023.

## Builds on (most cited first, 26 of 26)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts](https://mlsanity.com/paper/2110.01691/) (2021)
- [NL4DV: A Toolkit for Generating Analytic Specifications for Data Visualization from Natural Language Queries](https://mlsanity.com/paper/2008.10723/) (2020)
- [Towards Natural Language Interfaces for Data Visualization: A Survey](https://mlsanity.com/paper/2109.03506/) (2021)
- [Collecting and Characterizing Natural Language Utterances for Specifying Data Visualizations](https://mlsanity.com/paper/2110.00680/) (2021)
- [nvBench: A Large-Scale Synthesized Dataset for Cross-Domain Natural Language to Visualization Task](https://mlsanity.com/paper/2112.12926/) (2021)
- [FlowSense: A Natural Language Interface for Visual Data Exploration within a Dataflow System](https://mlsanity.com/paper/1908.00681/) (2019)
- [Iris: A Conversational Agent for Complex Tasks](https://mlsanity.com/paper/1707.05015/) (2017)
- [Towards Natural Language-Based Visualization Authoring](https://mlsanity.com/paper/2208.10947/) (2022)
- [Snowy: Recommending Utterances for Conversational Visual Analysis](https://mlsanity.com/paper/2110.04323/) (2021)
- [InChorus: Designing Consistent Multimodal Interactions for Data Visualization on Tablet Devices](https://mlsanity.com/paper/2001.06423/) (2020)
- [Facilitating Conversational Interaction in Natural Language Interfaces for Visualization](https://mlsanity.com/paper/2207.00189/) (2022)
- [Sporthesia: Augmenting Sports Videos Using Natural Language](https://mlsanity.com/paper/2209.03434/) (2022)
- [Quda: Natural Language Queries for Visual Data Analytics](https://mlsanity.com/paper/2005.03257/) (2020)
- [Persua: A Visual Interactive System to Enhance the Persuasiveness of Arguments in Online Discussion](https://mlsanity.com/paper/2204.07741/) (2022)
- [Interweaving Multimodal Interaction with Flexible Unit Visualizations for Data Exploration](https://mlsanity.com/paper/2004.10428/) (2020)
- [Beyond Interestingness: Semantic and Context-Aware Natural Language Query Recommendations for Visual Data Analysis](https://mlsanity.com/paper/2201.04868/) (2022)
- [Explaining Queries over Web Tables to Non-Experts](https://mlsanity.com/paper/1808.04614/) (2018)
- [Touch? Speech? or Touch and Speech? Investigating Multimodal Interaction for Visual Network Exploration and Analysis](https://mlsanity.com/paper/2004.14505/) (2020)
- [DeHumor: Visual Analytics for Decomposing Humor](https://mlsanity.com/paper/2107.08356/) (2021)
- [QueryVis: Logic-based diagrams help users understand complicated SQL queries faster](https://mlsanity.com/paper/2004.11375/) (2020)
- [Visualizing the Scripts of Data Wrangling with SOMNUS](https://mlsanity.com/paper/2209.13981/) (2022)
- [Table Scraps: An Actionable Framework for Multi-Table Data Wrangling From An Artifact Study of Computational Journalism](https://mlsanity.com/paper/2009.02373/) (2020)
- [RASIPAM: Interactive Pattern Mining of Multivariate Event Sequences in Racket Sports](https://mlsanity.com/paper/2208.00671/) (2022)
- [Comparison Conundrum and the Chamber of Visualizations: An Exploration of How Language Influences Visual Design](https://mlsanity.com/paper/2208.03785/) (2022)
- [GeoSneakPique: Visual Autocompletion for Geospatial Queries](https://mlsanity.com/paper/2110.12596/) (2021)

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

- [PromptMagician: Interactive Prompt Engineering for Text-to-Image Creation](https://mlsanity.com/paper/2307.09036/) (2023)
- [WaitGPT: Monitoring and Steering Conversational LLM Agent in Data Analysis with On-the-Fly Code Visualization](https://mlsanity.com/paper/2408.01703/) (2024)
- [AgentCoord: Visually Exploring Coordination Strategy for LLM-based Multi-Agent Collaboration](https://mlsanity.com/paper/2404.11943/) (2024)
- [AgentLens: Visual Analysis for Agent Behaviors in LLM-based Autonomous Systems](https://mlsanity.com/paper/2402.08995/) (2024)
- [JarviX: A LLM No code Platform for Tabular Data Analysis and Optimization](https://mlsanity.com/paper/2312.02213/) (2023)
- [Towards an Understanding and Explanation for Mixed-Initiative Artificial Scientific Text Detection](https://mlsanity.com/paper/2304.05011/) (2023)
- [JailbreakLens: Visual Analysis of Jailbreak Attacks Against Large Language Models](https://mlsanity.com/paper/2404.08793/) (2024)
- [DataLab: A Unified Platform for LLM-Powered Business Intelligence](https://mlsanity.com/paper/2412.02205/) (2024)
- [Data Analysis in the Era of Generative AI](https://mlsanity.com/paper/2409.18475/) (2024)
- [Exploring Multimodal Prompt for Visualization Authoring with Large Language Models](https://mlsanity.com/paper/2504.13700/) (2025)
- [ScrollTimes: Tracing the Provenance of Paintings as a Window into History](https://mlsanity.com/paper/2306.08834/) (2023)
- [CommonsenseVIS: Visualizing and Understanding Commonsense Reasoning Capabilities of Natural Language Models](https://mlsanity.com/paper/2307.12382/) (2023)
- [XGraphRAG: Interactive Visual Analysis for Graph-based Retrieval-Augmented Generation](https://mlsanity.com/paper/2506.13782/) (2025)
- [OW-CLIP: Data-Efficient Visual Supervision for Open-World Object Detection via Human-AI Collaboration](https://mlsanity.com/paper/2507.19870/) (2025)
- [Prismatic: Interactive Multi-View Cluster Analysis of Concept Stocks](https://mlsanity.com/paper/2402.08978/) (2024)
- [MiniGPT-Reverse-Designing: Predicting Image Adjustments Utilizing MiniGPT-4](https://mlsanity.com/paper/2406.00971/) (2024)
- [AdaLens: Interactive Storyline for Monitoring and Steering Long-Running Agentic Data Analysis](https://mlsanity.com/paper/2608.17834/) (2026)
- [Multi-Agent Discovery and Resource-Aware Autonomous Exploration of Scientific Datasets](https://mlsanity.com/paper/2608.22045/) (2026)
- [DataWeave: Deploying Human-LLM Analytics for Exploratory Structured Data Analysis](https://mlsanity.com/paper/2610.02679/) (2026)

## Abstract (arXiv)

Natural language interfaces (NLIs) enable users to flexibly specify analytical intentions in data visualization. However, diagnosing the visualization results without understanding the underlying generation process is challenging. Our research explores how to provide explanations for NLIs to help users locate the problems and further revise the queries. We present XNLI, an explainable NLI system for visual data analysis. The system introduces a Provenance Generator to reveal the detailed process of visual transformations, a suite of interactive widgets to support error adjustments, and a Hint Generator to provide query revision hints based on the analysis of user queries and interactions. Two usage scenarios of XNLI and a user study verify the effectiveness and usability of the system. Results suggest that XNLI can significantly enhance task accuracy without interrupting the NLI-based analysis process.