---
title: "DePlot — paper by Liu et al. (2023) — summary and ideas"
description: "Answering questions about charts and plots requires both precise extraction of the underlying values… 34 references, cited by 54 papers here."
authors: ["Fangyu Liu", "Julian Eisenschlos", "Francesco Piccinno", "Syrine Krichene", "Chenxi Pang", "Kenton Lee", "Mandar Joshi", "Wenhu Chen", "Nigel Collier", "Yasemin Altun"]
year: 2023
venue: "Findings of the Association for Computational Linguistics: ACL 2023"
source: "https://aclanthology.org/2023.findings-acl.660/"
doi: "10.18653/v1/2023.findings-acl.660"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/liu-2023-deplot-one-shot-visual-language/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/liu-2023-deplot-one-shot-visual-language/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2023](https://md.research.elamur.ai/free/en/papers/2023/page/5/) / DePlot: One-shot visual language reasoning by plot-to-table translation

# DePlot: One-shot visual language reasoning by plot-to-table translation

**Authors:** [Fangyu Liu](https://md.research.elamur.ai/free/en/authors/fangyu-liu/), [Julian Eisenschlos](https://md.research.elamur.ai/free/en/authors/julian-eisenschlos/), [Francesco Piccinno](https://md.research.elamur.ai/free/en/authors/francesco-piccinno/), [Syrine Krichene](https://md.research.elamur.ai/free/en/authors/syrine-krichene/), [Chenxi Pang](https://md.research.elamur.ai/free/en/authors/chenxi-pang/), [Kenton Lee](https://md.research.elamur.ai/free/en/authors/kenton-lee/), [Mandar Joshi](https://md.research.elamur.ai/free/en/authors/mandar-joshi/), [Wenhu Chen](https://md.research.elamur.ai/free/en/authors/wenhu-chen/), [Nigel Collier](https://md.research.elamur.ai/free/en/authors/nigel-collier/) and [Yasemin Altun](https://md.research.elamur.ai/free/en/authors/yasemin-altun/) · **Year:** 2023 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2023](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2023](https://md.research.elamur.ai/free/en/venues/findings/2023/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2023.findings-acl.660/) · [PDF](https://aclanthology.org/2023.findings-acl.660.pdf) · [DOI 10.18653/v1/2023.findings-acl.660](https://doi.org/10.18653/v1/2023.findings-acl.660) · [OpenAlex](https://openalex.org/W4385565485)

**Citations:** 67 citations (OpenAlex, 2026-10-14) · [54](https://md.research.elamur.ai/free/en/papers/liu-2023-deplot-one-shot-visual-language/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
Answering questions about charts and plots requires both precise extraction of the underlying values and multi-step numerical reasoning. Earlier end-to-end models needed tens of thousands of training examples and still performed poorly on complex questions written by humans. The authors split the problem into two stages. First, DePlot, an image-to-text Transformer, converts a chart into a linearized data table. Second, that table and the question go to an off-the-shelf large language model, which reasons over it from a single in-context example. To train and evaluate DePlot, they formalize plot-to-table conversion as a standard task. They also introduce a table-similarity metric that accounts for table structure, text and numbers. The training data combine synthetic charts with charts crawled from the web. With one-shot prompting, DePlot+LLM outperforms the fully supervised state of the art on human-written ChartQA queries by 29.4%. This suggests that converting a visual task into a text task lets few-shot LLM reasoning substitute for costly task-specific annotation.

## Key points
- **New metric (RMS).** The authors propose Relative Mapping Similarity (RMS) to replace the earlier RNSS measure. RNSS ignores where numbers sit in the table, discards non-numeric content and does not separate precision from recall. RMS is unaffected by transposition and by reordering rows or columns, and it tolerates small relative numeric errors.
- **Plot-to-table results.** DePlot outperformed an OCR-based pipeline (ChartOCR) and three end-to-end baselines. Unlike earlier hybrid systems, which were often built for one chart type, it handles all chart types with a single model.
- **Reasoning stage.** The LLMs used were FlanPaLM and Codex, with Chain-of-Thought, Self-Consistency and Program-of-Thoughts prompting. Evaluation covered ChartQA and PlotQA. The previous best model on ChartQA human queries, MatCha, reached only 38.2%.
- **Out-of-domain test.** On 10 manually annotated charts from the TaTa dataset (dhsprogram.com), DePlot reached about 78% RMS F1. It was distracted by nearby text and struggled with labels attached to chart elements by arrows.
- **Limitations.** Visual attributes such as color and orientation are lost during table conversion, so DePlot+LLM fails on questions about them. The approach also does not suit figures that lack a clear underlying table. Code and models are released in the google-research GitHub repository.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [University of Cambridge](https://md.research.elamur.ai/free/en/universities/university-of-cambridge/) — University, Cambridge, United Kingdom · 155 works · 115,562 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,085 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,888 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 1,282 works

🧭 Topics (2): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 510 works · [🖼️ Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) · 269 works

## Cite

Cite as: Fangyu Liu, Julian Eisenschlos, Francesco Piccinno, Syrine Krichene, Chenxi Pang, Kenton Lee, Mandar Joshi, Wenhu Chen, Nigel Collier and Yasemin Altun. 2023. DePlot: One-shot visual language reasoning by plot-to-table translation. Findings of the Association for Computational Linguistics: ACL 2023.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{liu2023deplot,
  title = {{DePlot: One-shot visual language reasoning by plot-to-table translation}},
  author = {Fangyu Liu, Julian Eisenschlos, Francesco Piccinno, Syrine Krichene, Chenxi Pang, Kenton Lee, Mandar Joshi, Wenhu Chen, Nigel Collier and Yasemin Altun},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2023},
  year = {2023},
  doi = {10.18653/v1/2023.findings-acl.660},
  url = {https://doi.org/10.18653/v1/2023.findings-acl.660}
}
```

- [← previous LEVER: Learning to Verify Language-to-Code Generation with Execution](https://md.research.elamur.ai/free/en/papers/ni-2023-lever-learning-verify-language-code/)
- [next → Generative Judge for Evaluating Alignment](https://md.research.elamur.ai/free/en/papers/li-2023-generative-judge-evaluating-alignment/)
- [↑ back to papers of 2023](https://md.research.elamur.ai/free/en/papers/2023/page/5/)

## References

34 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Mubashara Akhtar, Oana Cocarascu, and Elena Simperl. 2023. Reading and reasoning over chart images for evidence-based automated fact-checking. In Findings of the Association for Computational Linguistics: EACL 2023, pages 399–414, Dubrovnik, Croatia. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Mubashara+Akhtar%2C+Oana+Cocarascu%2C+and+Elena+Simperl%2E+2023%2E+Reading+and+reasoning+over+chart+images+for+evidence%2Dbased+automated+fact%2Dchecking%2E+In+Findings+of+the+Association+for+Computational+Linguist)
2. Ewa Andrejczuk, Julian Eisenschlos, Francesco Piccinno, Syrine Krichene, and Yasemin Altun. 2022. Table-to-text generation and pre-training with TabT5. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 6758–6766, Abu Dhabi, United Arab Emirates. Association for Computat… [find](https://scholar.google.com/scholar?q=Ewa+Andrejczuk%2C+Julian+Eisenschlos%2C+Francesco+Piccinno%2C+Syrine+Krichene%2C+and+Yasemin+Altun%2E+2022%2E+Table%2Dto%2Dtext+generation+and+pre%2Dtraining+with+TabT5%2E+In+Findings+of+the+Association+for+Computational)
3. A. Furkan Biten, R. Tito, A. Mafla, L. Gomez, M. Rusinol, M. Mathew, C. Jawahar, E. Valveny, and D. Karatzas. 2019. [find](https://scholar.google.com/scholar?q=A%2E+Furkan+Biten%2C+R%2E+Tito%2C+A%2E+Mafla%2C+L%2E+Gomez%2C+M%2E+Rusinol%2C+M%2E+Mathew%2C+C%2E+Jawahar%2C+E%2E+Valveny%2C+and+D%2E+Karatzas%2E+2019%2E)
4. Icdar 2019 competition on scene text visual question answering. In 2019 International Conference on Document Analysis and Recognition (ICDAR), pages 1563–1570, Los Alamitos, CA, USA. IEEE Computer Society. [find](https://scholar.google.com/scholar?q=Icdar+2019+competition+on+scene+text+visual+question+answering%2E+In+2019+International+Conference+on+Document+Analysis+and+Recognition+%28ICDAR%29%2C+pages+1563%E2%80%931570%2C+Los+Alamitos%2C+CA%2C+USA%2E+IEEE+Computer+Soc)
5. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in neural information processing systems, 33:1877–1901.
6. Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harrison Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, Alex Ray, Raul Puri, Gretchen Krueger, Michael Petrov, Heidy Khlaaf, Girish Sastry, Pamela Mishkin, Brooke Chan, Scott Gray, Nick Ryder, Mik… — [Large Language Models are few(1)-shot Table Reasoners](https://md.research.elamur.ai/free/en/papers/chen-2023-large-language-models-are-few/)
7. Wenhu Chen, Xueguang Ma, Xinyi Wang, and William W Cohen. 2022. Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks. arXiv preprint arXiv:2211.12588. [find](https://scholar.google.com/scholar?q=Wenhu+Chen%2C+Xueguang+Ma%2C+Xinyi+Wang%2C+and+William+W+Cohen%2E+2022%2E+Program+of+thoughts+prompting%3A+Disentangling+computation+from+reasoning+for+numerical+reasoning+tasks%2E+arXiv+preprint+arXiv%3A2211%2E12588%2E)
8. Xi Chen, Xiao Wang, Soravit Changpinyo, AJ Piergiovanni, Piotr Padlewski, Daniel Salz, Sebastian Goodman, Adam Grycner, Basil Mustafa, Lucas Beyer, et al. 2023. [Pali: A jointly-scaled multilingual language-image model](https://md.research.elamur.ai/free/en/papers/chen-2022-pali-jointly-scaled-multilingual-language/). In The Eleventh International Conference on Learning Representations.
9. Zhoujun Cheng, Tianbao Xie, Peng Shi, Chengzu Li, Rahul Nadkarni, Yushi Hu, Caiming Xiong, Dragomir Radev, Mari Ostendorf, Luke Zettlemoyer, et al. 2023. [Binding language models in symbolic languages](https://md.research.elamur.ai/free/en/papers/cheng-2022-binding-language-models-symbolic-languages/). In The Eleventh International Conference on Learning Representations.
10. Jaemin Cho, Jie Lei, Hao Tan, and Mohit Bansal. 2021. Unifying vision-and-language tasks via text generation. In International Conference on Machine Learning, pages 1931–1942. PMLR. [find](https://scholar.google.com/scholar?q=Jaemin+Cho%2C+Jie+Lei%2C+Hao+Tan%2C+and+Mohit+Bansal%2E+2021%2E+Unifying+vision%2Dand%2Dlanguage+tasks+via+text+generation%2E+In+International+Conference+on+Machine+Learning%2C+pages+1931%E2%80%931942%2E+PMLR%2E)
11. Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. 2022. [PaLM: Scaling language modeling with pathways](https://md.research.elamur.ai/free/en/papers/chowdhery-2022-palm-scaling-language-modeling-pathways/). arXiv preprint arXiv:2204.02311.
12. Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Eric Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, et al. 2022. Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416. [find](https://scholar.google.com/scholar?q=Hyung+Won+Chung%2C+Le+Hou%2C+Shayne+Longpre%2C+Barret+Zoph%2C+Yi+Tay%2C+William+Fedus%2C+Eric+Li%2C+Xuezhi+Wang%2C+Mostafa+Dehghani%2C+Siddhartha+Brahma%2C+et+al%2E+2022%2E+Scaling+instruction%2Dfinetuned+language+models%2E+arXi)
13. Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2021. [An image is worth 16x16 words: Transformers for image recognition at scale](https://md.research.elamur.ai/free/en/papers/dosovitskiy-2020-image-worth-16x16-words-transformers/). In International Conference on Learni…
14. Luyu Gao, Aman Madaan, Shuyan Zhou, Uri Alon, Pengfei Liu, Yiming Yang, Jamie Callan, and Graham Neubig. 2022. PAL: Program-aided language models. arXiv preprint arXiv:2211.10435. [find](https://scholar.google.com/scholar?q=Luyu+Gao%2C+Aman+Madaan%2C+Shuyan+Zhou%2C+Uri+Alon%2C+Pengfei+Liu%2C+Yiming+Yang%2C+Jamie+Callan%2C+and+Graham+Neubig%2E+2022%2E+PAL%3A+Program%2Daided+language+models%2E+arXiv+preprint+arXiv%3A2211%2E10435%2E)
15. Sebastian Gehrmann, Sebastian Ruder, Vitaly Nikolaev, Jan A Botha, Michael Chavinda, Ankur Parikh, and Clara Rivera. 2022. TaTa: A multilingual table-to-text dataset for african languages. arXiv preprint arXiv:2211.00142. [find](https://scholar.google.com/scholar?q=Sebastian+Gehrmann%2C+Sebastian+Ruder%2C+Vitaly+Nikolaev%2C+Jan+A+Botha%2C+Michael+Chavinda%2C+Ankur+Parikh%2C+and+Clara+Rivera%2E+2022%2E+TaTa%3A+A+multilingual+table%2Dto%2Dtext+dataset+for+african+languages%2E+arXiv+prepr)
16. Jonathan Herzig, Pawel Krzysztof Nowak, Thomas Müller, Francesco Piccinno, and Julian Eisenschlos. 2020. [TaPas: Weakly supervised table parsing via pre-training](https://md.research.elamur.ai/free/en/papers/herzig-2020-tapas-weakly-supervised-table-parsing/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4320–4333, Online. Association for Compu…
17. Shankar Kantharaj, Rixie Tiffany Leong, Xiang Lin, Ahmed Masry, Megh Thakkar, Enamul Hoque, and Shafiq Joty. 2022. [Chart-to-text: A large-scale benchmark for chart summarization](https://md.research.elamur.ai/free/en/papers/kantharaj-2022-chart-text-large-scale-benchmark/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages…
18. Ahmed Masry, Do Long, Jia Qing Tan, Shafiq Joty, and Enamul Hoque. 2022. [ChartQA: A benchmark for question answering about charts with visual and logical reasoning](https://md.research.elamur.ai/free/en/papers/masry-2022-chartqa-benchmark-question-answering-about/). In Findings of the Association for Computational Linguistics: ACL 2022, pages 2263–2279, Dublin, Ireland. Association for Computational…
19. Nitesh Methani, Pritha Ganguly, Mitesh M Khapra, and Pratyush Kumar. 2020. PlotQA: Reasoning over scientific plots. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 1527–1536. [find](https://scholar.google.com/scholar?q=Nitesh+Methani%2C+Pritha+Ganguly%2C+Mitesh+M+Khapra%2C+and+Pratyush+Kumar%2E+2020%2E+PlotQA%3A+Reasoning+over+scientific+plots%2E+In+Proceedings+of+the+IEEE%2FCVF+Winter+Conference+on+Applications+of+Computer+Vision%2C)
20. OpenAI. 2023. [GPT-4 Technical Report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). preprint arXiv:2303.08774. arXiv Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervisio…
21. Hajime Kato, Mitsuru Nakazawa, Hsuan-Kung Yang, Mark Chen, and Björn Stenger. 2022. Parsing line chart images using linear programming. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 2109–2118. [find](https://scholar.google.com/scholar?q=Hajime+Kato%2C+Mitsuru+Nakazawa%2C+Hsuan%2DKung+Yang%2C+Mark+Chen%2C+and+Bj%C3%B6rn+Stenger%2E+2022%2E+Parsing+line+chart+images+using+linear+programming%2E+In+Proceedings+of+the+IEEE%2FCVF+Winter+Conference+on+Applications)
22. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J Liu, et al. 2020. [Exploring the limits of transfer learning with a unified text-to-text transformer](https://md.research.elamur.ai/free/en/papers/raffel-2019-exploring-limits-transfer-learning-unified/). J. Mach. Learn. Res., 21(140):1–67.
23. Kenton Lee, Mandar Joshi, Iulia Turc, Hexiang Hu, Fangyu Liu, Julian Eisenschlos, Urvashi Khandelwal, Peter Shaw, Ming-Wei Chang, and Kristina Toutanova. 2023. Pix2Struct: Screenshot parsing as pretraining for visual language understanding. In Proceedings of the 40th International Conference on Mach… [find](https://scholar.google.com/scholar?q=Kenton+Lee%2C+Mandar+Joshi%2C+Iulia+Turc%2C+Hexiang+Hu%2C+Fangyu+Liu%2C+Julian+Eisenschlos%2C+Urvashi+Khandelwal%2C+Peter+Shaw%2C+Ming%2DWei+Chang%2C+and+Kristina+Toutanova%2E+2023%2E+Pix2Struct%3A+Screenshot+parsing+as+pretra)
24. Chinmayee Rane, Seshasayee Mahadevan Subramanya, Devi Sandeep Endluri, Jian Wu, and C Lee Giles. 2021. ChartReader: Automatic parsing of barplots. In 2021 IEEE 22nd International Conference on Information Reuse and Integration for Data Science (IRI), pages 318–325. IEEE. [find](https://scholar.google.com/scholar?q=Chinmayee+Rane%2C+Seshasayee+Mahadevan+Subramanya%2C+Devi+Sandeep+Endluri%2C+Jian+Wu%2C+and+C+Lee+Giles%2E+2021%2E+ChartReader%3A+Automatic+parsing+of+barplots%2E+In+2021+IEEE+22nd+International+Conference+on+Informa)
25. Matan Levy, Rami Ben-Ari, and Dani Lischinski. 2022. Classification-regression for chart comprehension. In European Conference on Computer Vision, pages 469–484. Springer. [find](https://scholar.google.com/scholar?q=Matan+Levy%2C+Rami+Ben%2DAri%2C+and+Dani+Lischinski%2E+2022%2E+Classification%2Dregression+for+chart+comprehension%2E+In+European+Conference+on+Computer+Vision%2C+pages+469%E2%80%93484%2E+Springer%2E)
26. Noah Siegel, Zachary Horvitz, Roie Levin, Santosh Divvala, and Ali Farhadi. 2016. FigureSeer: Parsing result-figures in research papers. In European Conference on Computer Vision, pages 664–680. Springer. [find](https://scholar.google.com/scholar?q=Noah+Siegel%2C+Zachary+Horvitz%2C+Roie+Levin%2C+Santosh+Divvala%2C+and+Ali+Farhadi%2E+2016%2E+FigureSeer%3A+Parsing+result%2Dfigures+in+research+papers%2E+In+European+Conference+on+Computer+Vision%2C+pages+664%E2%80%93680%2E+Sprin)
27. Fangyu Liu, Francesco Piccinno, Syrine Krichene, Chenxi Pang, Kenton Lee, Mandar Joshi, Nigel Collier, Yasemin Altun, and Julian Martin Eisenschlos. 2023a. MatCha: Enhancing visual language pre-training with math reasoning and chart derendering. In Proceedings of the 61st Annual Meeting of the Assoc… [find](https://scholar.google.com/scholar?q=Fangyu+Liu%2C+Francesco+Piccinno%2C+Syrine+Krichene%2C+Chenxi+Pang%2C+Kenton+Lee%2C+Mandar+Joshi%2C+Nigel+Collier%2C+Yasemin+Altun%2C+and+Julian+Martin+Eisenschlos%2E+2023a%2E+MatCha%3A+Enhancing+visual+language+pre%2Dtraini)
28. Ruibo Liu, Jason Wei, Shixiang Shane Gu, Te-Yen Wu, Soroush Vosoughi, Claire Cui, Denny Zhou, and Andrew M Dai. 2023b. Mind’s eye: Grounded language model reasoning through simulation. In The Eleventh International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Ruibo+Liu%2C+Jason+Wei%2C+Shixiang+Shane+Gu%2C+Te%2DYen+Wu%2C+Soroush+Vosoughi%2C+Claire+Cui%2C+Denny+Zhou%2C+and+Andrew+M+Dai%2E+2023b%2E+Mind%E2%80%99s+eye%3A+Grounded+language+model+reasoning+through+simulation%2E+In+The+Eleventh)
29. Junyu Luo, Zekun Li, Jinpeng Wang, and Chin-Yew Lin. 2021. ChartOCR: Data extraction from charts Yixuan Su, Tian Lan, Yahui Liu, Fangyu Liu, Dani Yogatama, Yan Wang, Lingpeng Kong, and Nigel Collier. 2022. Language models can see: Plugging visual controls in text generation. arXiv preprint arXiv:220… — [arXiv:2205.02655](https://arxiv.org/abs/2205.02655) [find](https://scholar.google.com/scholar?q=Junyu+Luo%2C+Zekun+Li%2C+Jinpeng+Wang%2C+and+Chin%2DYew+Lin%2E+2021%2E+ChartOCR%3A+Data+extraction+from+charts+Yixuan+Su%2C+Tian+Lan%2C+Yahui+Liu%2C+Fangyu+Liu%2C+Dani+Yogatama%2C+Yan+Wang%2C+Lingpeng+Kong%2C+and+Nigel+Collier%2E+)
30. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023. [Self-consistency improves chain of thought reasoning in language models](https://md.research.elamur.ai/free/en/papers/wang-2022-self-consistency-improves-chain-thought/). In The Eleventh International Conference on Learning Representations.
31. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, brian ichter, Fei Xia, Ed H. Chi, Quoc V Le, and Denny Zhou. 2022. [Chain of thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). In Advances in Neural Information Processing Systems.
32. Zhengyuan Yang, Zhe Gan, Jianfeng Wang, Xiaowei Hu, Yumao Lu, Zicheng Liu, and Lijuan Wang. 2022. An empirical study of gpt-3 for few-shot knowledge-based vqa. Proceedings of the AAAI Conference on Artificial Intelligence, 36(3):3081– 3089. [find](https://scholar.google.com/scholar?q=Zhengyuan+Yang%2C+Zhe+Gan%2C+Jianfeng+Wang%2C+Xiaowei+Hu%2C+Yumao+Lu%2C+Zicheng+Liu%2C+and+Lijuan+Wang%2E+2022%2E+An+empirical+study+of+gpt%2D3+for+few%2Dshot+knowledge%2Dbased+vqa%2E+Proceedings+of+the+AAAI+Conference+on+Ar)
33. Pengcheng Yin, Graham Neubig, Wen-tau Yih, and Sebastian Riedel. 2020. [TaBERT: Pretraining for joint understanding of textual and tabular data](https://md.research.elamur.ai/free/en/papers/yin-2020-tabert-pretraining-joint-understanding-textual/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8413– 8426, Online. Association for Computational Linguist…
34. Andy Zeng, Maria Attarian, brian ichter, Krzysztof Marcin Choromanski, Adrian Wong, Stefan Welker, Federico Tombari, Aveek Purohit, Michael S Ryoo, Vikas Sindhwani, Johnny Lee, Vincent Vanhoucke, and Pete Florence. 2023. [Socratic models: Composing zero-shot multimodal reasoning with language](https://md.research.elamur.ai/free/en/papers/zeng-2022-socratic-models-composing-zero-shot/). In The…

*Updated 24 October 2026*