Chart-based Reasoning: Transferring Capabilities from LLMs to VLMs

Victor Carbune, Hassan Mansoor, Fangyu Liu, Rahul Aralikatte, Gilles Baechler, Jindong Chen, Abhanshu Sharma


Abstract
Vision-language models (VLMs) are achieving increasingly strong performance on multimodal tasks. However, reasoning capabilities remain limited particularly for smaller VLMs, while those of large-language models (LLMs) have seen numerous improvements. We pro-pose a technique to transfer capabilities from LLMs to VLMs. On the recently introduced ChartQA, our method obtains state-of-the-artperformance when applied on the PaLI3-5B VLM by Chen et al. (2023c), while also enabling much better performance on PlotQA and FigureQA.We first improve the chart representation by continuing the pre-training stage using an improved version of the chart-to-table translation task by Liu et al. (2023a). We then propose constructing a 20x larger dataset than the original training set. To improve general reasoning capabilities and improve numerical operations, we synthesize reasoning traces using the table representation of charts. Lastly, our model is fine-tuned using the multitask loss introduced by Hsieh et al. (2023).Our variant ChartPaLI-5B outperforms even 10x larger models such as PaLIX-55B without using an upstream OCR system, while keeping inference time constant compared to the PaLI3-5B baseline. When rationales are further refined with a simple program-of-thought prompt (Chen et al., 2023a), our model outperforms the recently introduced Gemini Ultra and GPT-4V.
Anthology ID:
2024.findings-naacl.62
Volume:
Findings of the Association for Computational Linguistics: NAACL 2024
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
989–1004
Language:
URL:
https://aclanthology.org/2024.findings-naacl.62
DOI:
Bibkey:
Cite (ACL):
Victor Carbune, Hassan Mansoor, Fangyu Liu, Rahul Aralikatte, Gilles Baechler, Jindong Chen, and Abhanshu Sharma. 2024. Chart-based Reasoning: Transferring Capabilities from LLMs to VLMs. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 989–1004, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Chart-based Reasoning: Transferring Capabilities from LLMs to VLMs (Carbune et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-naacl.62.pdf
Copyright:
 2024.findings-naacl.62.copyright.pdf