Philipp/Konferenzseminar-ML-PAL
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Added result table
Some checks failed
Latex Build / LatexBuild (push) Failing after 10m51s
Details

Browse Source
This commit is contained in:
Philipp Horstenkamp
2023-12-09 00:11:46 +01:00
parent ed1f9ecc0c
commit 40ac0eb6e9
1 changed files with 32 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
pal-vorstellung.tex
View File

@ -16,7 +16,7 @@
\lstset{basicstyle=\footnotesize\ttfamily, breaklines=true, keepspaces=true, columns=fixed, numberstyle=\tiny, keywordstyle=\color{blue}}
\usepackage{tikz}
\usetikzlibrary{positioning,fit,calc,backgrounds}
\usepackage{tabularray}
\renewcommand{\lstlistingname}{Codebeispiel}
@ -211,7 +211,37 @@ def soloution()
return sum(vegetables_to_count.values())
\end{lstlisting}
\section{}
\section{Ergebnisse}
\begin{table*}
\centering
\resizebox{\linewidth}{!}{%
\begin{tabular}{ll|cccccccc}
\hline
Algorithm & LLM & GSM8K & GSM-HARD & SVAMP & ASDIV & SINGLEEQ & SINGLEOP & ADDSUB & MULTIARITH \\
\hline
DIRECT & Codex & 19.7 & 5.0 & 69.9 & 74.0 & 86.8 & 93.1 & 90.9 & 44.0 \\
CoT & UL2-20B & 4.1 & - & 12.6 & 16.9 & - & - & 18.2 & 10.7 \\
CoT & LAMBDA-137B & 17.1 & - & 39.9 & 49.0 & - & - & 52.9 & 51.8 \\
CoT & Codex & 65.6 & 23.1 & 74.8 & 76.9 & 89.1 & 91.9 & 86.0 & 95.9 \\
CoT & PaLM-540B & 56.9 & - & 79.0 & 73.9 & 92.3 & 94.1 & 91.9 & 94.7 \\
CoT & Minerva 540B & 58.8 & - & - & - & - & - & - & - \\
PAL & & 72.0 & 61.2 & 79.4 & 79.6 & 96.1 & 94.6 & 92.5 & 99.2 \\
\hline
\end{tabular}
}
\caption{Model performance on various tasks}
\label{tab:model_performance}
\end{table*}
\subsection{Ergebnisse der mathematischen Aufgaben}
\subsection{Ergebnisse der Aufgaben zum Abstrakten Denken}
\subsection{Ergebnisse zu Algorithmischen Aufgaben}
\section{Ausblick}