MétaCan
Menu
Back to cohort

Are Large Vision Language Models up to the Challenge of Chart Comprehension and Reasoning

2024· article· en· W4404781890 on OpenAlexfundno aff
Mohammed Saidul Islam, Raian Rahman, Ahmed Masry, Md Tahmid Rahman Laskar, Mir Tafseer Nayeem, Enamul Hoque

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicNatural Language Processing Techniques
Canadian institutionsnot available
FundersNatural Sciences and Engineering Research Council of CanadaCompute CanadaCentre International de Recherche sur le Cancer
KeywordsComputer scienceComprehensionChartNatural language processingArtificial intelligenceProgramming languageStatisticsMathematics

Abstract

fetched live from OpenAlex

Natural language is a powerful complementary modality of communication for data visualizations, such as bar and line charts.To facilitate chart-based reasoning using natural language, various downstream tasks have been introduced recently such as chart question answering, chart summarization, and fact-checking with charts.These tasks pose a unique challenge, demanding both vision-language reasoning and a nuanced understanding of chart data tables, visual encodings, and natural language instructions.Despite the recent success of Large Language Models (LLMs) across diverse NLP tasks, their abilities and limitations in the realm of data visualization remain under-explored, possibly due to their lack of multi-modal capabilities.To bridge the gap, this paper presents one of the first comprehensive evaluations of the recently developed large vision language models (LVLMs) for chart understanding and reasoning tasks.Our evaluation includes a comprehensive assessment of both closed and opensourced LVLMs across five major chart reasoning tasks.Furthermore, we perform a qualitative evaluation of LVLMs' performance on a diverse range of charts, aiming to provide a thorough analysis.Our findings reveal that while LVLMs demonstrate impressive abilities in generating fluent texts covering high-level data insights, they also encounter common problems like hallucinations, factual errors, and data bias.We highlight the key strengths and limitations of LVLMs in chart comprehension tasks, offering insights for future research 1 .* Equal contribution. 1 We make all our prompts as well as LVLMs' responses open source here. Chart Question-AnsweringSummary: The first two cases of the new coronavirus (COVID-19) in Italy were recorded between the end of January and the beginning of February 2020 .As of January 5 , 2021 , there were 569,161 thousand active coronavirus cases in the country .The highest figure was recorded on November 22 , 2020 , when the number of active coronavirus cases was equal to 805,947 .Also , the total number of cases (including active cases , recoveries , and deaths) in Italy surpassed 2.1 million .Question: What's the sum of median value of blue and green graph?Answer: 87.5 Chart Summarization Question:Compare the Democrats and Republicans views about providing healthcare to the Population Answer: While 83% of Democrats say providing high quality, affordable healthcare for all should be top priority, a much smaller share of Republicans (48%) agree. Open-ended Chart Question-AnsweringStatement: Ea patras is the only club to be established before 1900

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.006
metaresearch head score (Gemma)0.041
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.007
Threshold uncertainty score0.031

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0060.041
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0010.001
Science and technology studies0.0000.002
Scholarly communication0.0040.011
Open science0.0020.003
Research integrity0.0020.004
Insufficient payload (model declined to judge)0.0070.003

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.019
GPT teacher head0.303
Teacher spread0.284 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations6
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicNatural Language Processing TechniquesFrench-language works237,207