Pith. sign in

REVIEW 5 cited by

ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.09028 v1 pith:BRI72GWE submitted 2024-03-14 cs.CL

classification cs.CL
keywords taskschartmodelsapplicabilityapproachchart-relatedchartinstructcharts
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Charts provide visual representations of data and are widely used for analyzing information, addressing queries, and conveying insights to others. Various chart-related downstream tasks have emerged recently, such as question-answering and summarization. A common strategy to solve these tasks is to fine-tune various models originally trained on vision tasks language. However, such task-specific models are not capable of solving a wide range of chart-related tasks, constraining their real-world applicability. To overcome these challenges, we introduce ChartInstruct: a novel chart-specific vision-language Instruction-following dataset comprising 191K instructions generated with 71K charts. We then present two distinct systems for instruction tuning on such datasets: (1) an end-to-end model that connects a vision encoder for chart understanding with a LLM; and (2) a pipeline model that employs a two-step approach to extract chart data tables and input them into the LLM. In experiments on four downstream tasks, we first show the effectiveness of our model--achieving a new set of state-of-the-art results. Further evaluation shows that our instruction-tuning approach supports a wide array of real-world chart comprehension and reasoning scenarios, thereby expanding the scope and applicability of our models to new kinds of tasks.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. ChartCap: Mitigating Hallucination of Dense Chart Captioning

    cs.CV 2025-08 conditional novelty 7.0 of 10

    A new 565K-pair chart-caption dataset with schema-based dense captions and a reference-free visual consistency metric improves VLM captioning and reduces hallucination.

  2. ChartMind: A Comprehensive Benchmark for Complex Real-world Multimodal Chart Question Answering

    cs.CL 2025-05 conditional novelty 5.0 of 10

    ChartMind is a new bilingual chart QA benchmark, and ChartLLM's structured context extraction yields higher scores than three existing prompting paradigms in the paper's evaluations.

  3. CHAOS: Chart Analysis with Outlier Samples

    cs.CV 2025-05 conditional novelty 5.0 of 10

    A chart perturbation robustness benchmark with five textual and ten visual distortion types, three human-calibrated severity levels, and evaluations of 13 MLLMs on ChartQA and chart summarization.

  4. Adaptive Sparse Softmax: An Effective and Efficient Softmax Variant

    cs.LG 2025-08 unverdicted novelty 4.0 of 10

    The preprint's abstract claims a sparse softmax variant that masks non-competitive classes and accelerates training, but the provided body contains an unrelated chart-captioning paper and none of the claimed method.

  5. ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding

    cs.CV 2025-05 conditional novelty 4.0 of 10

    ChartSketcher has a multimodal LLM sketch intermediate reasoning steps directly on chart images and feed those sketches back as visual feedback, improving chart QA accuracy over its base model.

Pith tools