TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Data
Open paper
Benchmark
Model
Rank
Results
question-answering-on-tat-qa
TAT-LLM (70B)
#1
F1: 88.4
Exact Match: 81.4
question-answering-on-tat-qa
TAT-LLM (13B)
#2
F1: 85.9
Exact Match: 77.5
question-answering-on-tat-qa
TAT-LLM (7B)
#3
F1: 85.1
Exact Match: 76.4
Rank counts only results with a code link.