# DOMINO: A Dual-System for Multi-step Visual Language Reasoning

arXiv: https://arxiv.org/abs/2310.02804 · HTML: https://mlsanity.com/paper/2310.02804/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 28 of its 34 references that are in the map.
- First posted on arXiv 4 Oct 2023.

## Placed in

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

## Builds on (most cited first, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding](https://mlsanity.com/paper/2210.03347/) (2022)
- [DVQA: Understanding Data Visualizations via Question Answering](https://mlsanity.com/paper/1801.08163/) (2018)
- [PlotQA: Reasoning over Scientific Plots](https://mlsanity.com/paper/1909.00997/) (2019)
- [FigureQA: An Annotated Figure Dataset for Visual Reasoning](https://mlsanity.com/paper/1710.07300/) (2017)
- [Inductive Biases for Deep Learning of Higher-Level Cognition](https://mlsanity.com/paper/2011.15091/) (2020)
- [PaLI-X: On Scaling up a Multilingual Vision and Language Model](https://mlsanity.com/paper/2305.18565/) (2023)
- [Binding Language Models in Symbolic Languages](https://mlsanity.com/paper/2210.02875/) (2022)
- [DePlot: One-shot visual language reasoning by plot-to-table translation](https://mlsanity.com/paper/2212.10505/) (2022)
- [UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning](https://mlsanity.com/paper/2305.14761/) (2023)
- [MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering](https://mlsanity.com/paper/2212.09662/) (2022)
- [Large Language Models are few(1)-shot Table Reasoners](https://mlsanity.com/paper/2210.06710/) (2022)
- [LEAF-QA: Locate, Encode & Attend for Figure Question Answering](https://mlsanity.com/paper/1907.12861/) (2019)
- [Reading and Reasoning over Chart Images for Evidence-based Automated Fact-Checking](https://mlsanity.com/paper/2301.11843/) (2023)
- [Answering Questions about Data Visualizations using Efficient Bimodal Fusion](https://mlsanity.com/paper/1908.01801/) (2019)
- [Chart Question Answering: State of the Art and Future Directions](https://mlsanity.com/paper/2205.03966/) (2022)
- [ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules](https://mlsanity.com/paper/2304.02173/) (2023)
- [Chart-Text: A Fully Automated Chart Image Descriptor](https://mlsanity.com/paper/1812.10636/) (2018)
- [Table-To-Text generation and pre-training with TabT5](https://mlsanity.com/paper/2210.09162/) (2022)
- [ALERT: Adapting Language Models to Reasoning Tasks](https://mlsanity.com/paper/2212.08286/) (2022)

## Built on by (most cited first, 12 of 12)

- [ChartBench: A Benchmark for Complex Visual Reasoning in Charts](https://mlsanity.com/paper/2312.15915/) (2023)
- [ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning](https://mlsanity.com/paper/2403.09028/) (2024)
- [From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models](https://mlsanity.com/paper/2403.12027/) (2024)
- [ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understanding](https://mlsanity.com/paper/2409.03277/) (2024)
- [mChartQA: A universal benchmark for multimodal Chart Question Answer based on Vision-Language Alignment and Reasoning](https://mlsanity.com/paper/2404.01548/) (2024)
- [ChartMind: A Comprehensive Benchmark for Complex Real-world Multimodal Chart Question Answering](https://mlsanity.com/paper/2505.23242/) (2025)
- [ChartPoint: Guiding MLLMs with Grounding Reflection for Chart Reasoning](https://mlsanity.com/paper/2512.00305/) (2025)
- [Thinker-DDM: Modeling Deliberation for Machine Translation with a Drift-Diffusion Process](https://mlsanity.com/paper/2402.10699/) (2024)
- [Towards Child-Inclusive Clinical Video Understanding for Autism Spectrum Disorder](https://mlsanity.com/paper/2409.13606/) (2024)
- [Chain of Functions: A Programmatic Pipeline for Fine-Grained Chart Reasoning Data](https://mlsanity.com/paper/2503.16260/) (2025)
- [How Vision-Language Tasks Benefit from Large Pre-trained Models: A Survey](https://mlsanity.com/paper/2412.08158/) (2024)
- [CharTool: Tool-Integrated Visual Reasoning for Chart Understanding](https://mlsanity.com/paper/2604.02794/) (2026)

## Abstract (arXiv)

Visual language reasoning requires a system to extract text or numbers from information-dense images like charts or plots and perform logical or arithmetic reasoning to arrive at an answer. To tackle this task, existing work relies on either (1) an end-to-end vision-language model trained on a large amount of data, or (2) a two-stage pipeline where a captioning model converts the image into text that is further read by another large language model to deduce the answer. However, the former approach forces the model to answer a complex question with one single step, and the latter approach is prone to inaccurate or distracting information in the converted text that can confuse the language model. In this work, we propose a dual-system for multi-step multimodal reasoning, which consists of a "System-1" step for visual information extraction and a "System-2" step for deliberate reasoning. Given an input, System-2 breaks down the question into atomic sub-steps, each guiding System-1 to extract the information required for reasoning from the image. Experiments on chart and plot datasets show that our method with a pre-trained System-2 module performs competitively compared to prior work on in- and out-of-distribution data. By fine-tuning the System-2 module (LLaMA-2 70B) on only a small amount of data on multi-step reasoning, the accuracy of our method is further improved and surpasses the best fully-supervised end-to-end approach by 5.7% and a pipeline approach with FlanPaLM (540B) by 7.5% on a challenging dataset with human-authored questions.