Re:Automatic Generation of Visualizations and Infographics w...
by computerex on Tuesday August 29, 2023 @11:52AM
(#37309739)
Telling the LLM that it must do something is not a guarantee that it'll follow through.
Re:Automatic Generation of Visualizations and Infographics w...
by vykthur on Tuesday August 29, 2023 @04:36PM
(#37313635)
True. This is an open area of research. Tools like guidance (or other implementations of constrained decoding with llms [1,2]) will likely help improve this problem.
[1] A guidance language for controlling large language models. https://github.com/guidance-ai/guidance
[2] Knowledge Infused Decoding https://arxiv.org/abs/2204.03084
They prompted that things MUST be correct in their prompts and it reports any transformations it does to your data, it might give you some insight into its logic to test yourself against the data.