knowledge-graph-learning icon indicating copy to clipboard operation
knowledge-graph-learning copied to clipboard

Published 20 hours ago • verified publisher icon BrambleXu

WSDM-2024/03-Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study

Open BrambleXu opened this issue 11 months ago • 0 comments

Summary:

What input designs and choices are the most effective in enabling LLMs to understand tables?

Resource:

  • blog
  • pdf
  • [code](
  • [paper-with-code](

Paper information:

  • Author:
  • Dataset:
  • keywords:

Notes:

What input designs and choices are the most effective in enabling LLMs to understand tables?

image image image
  • Merged Cell Detection
  • Cell Lookup & Reverse Lookup
  • Column & Row Retrieval
image

Model Graph:

Result:：

Thoughts:

Next Reading:

BrambleXu avatar Mar 13 '24 04:03 BrambleXu