This project is focused on improving the performance of LLMs for numerical problems and its reliability over tabular data. Paper link: https://arxiv.org/pdf/2410. ...
This repository also includes a collection of evaluation scripts for table-related benchmarks. The evaluation scripts and datasets can be found in the realtabbench directory. For more details, please ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback