Hacker News Reader

Interesting, thanks for sharing! I was wondering about this. When starting out with feeding Tabular data, I instinctively went with CSV, but always worried: What if there is a better choice? What if longer tables, the LLMs forgets the column order?

View on HN

That's exactly what happened to me when I tried to get the open-source models to extract a CSV from textual data with a lot of yes/no fields; i.e., the model forgot the column order and started confusing the cell values. I found I had to use more powerful models like Mistral Large or ChatGPT. So I think that is a valid thing to worry about with smaller models, but maybe less of a concern with larger ones.

Have you ever figured out a way to annotate the CSV columns to the model? Or do you write a long prefix explaining the columns?

I found that similarly-named columns easily confused GPTs

Reply on news.ycombinator.com