Experiment to test chart selection

[01painadam]

Summary

What does this research help us do? What future work will this unlock or what decisions it enable?

When a result returns, the LLM must select an appropriate chart for that data: tables for rankings, line chart for time series, bars for yearly aggregated data, donut charts for categorical data etc

Key questions

(no more than 5) What do we want this spike to answer? Focus on outcomes.

1. How well is the model able to select an appropriate data visualisation type, given the data?

Expected Output(s)

What artefacts do we expect to produce that will help us answer the above questions? May be designs, documents, a prototype feature…

• notebook
• go/no decision

Hints

Suggestions about how to go about the research. How might we answer these questions?