diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..ccc9fd9 --- /dev/null +++ b/.gitignore @@ -0,0 +1 @@ +*.DS_Store \ No newline at end of file diff --git a/NeurIPS-tut-LLM-watermark-part-1.pdf b/NeurIPS-tut-LLM-watermark-part-1.pdf new file mode 100644 index 0000000..e7d74bf Binary files /dev/null and b/NeurIPS-tut-LLM-watermark-part-1.pdf differ diff --git a/NeurIPS-tut-LLM-watermark-part-2.pdf b/NeurIPS-tut-LLM-watermark-part-2.pdf new file mode 100644 index 0000000..a4c943b Binary files /dev/null and b/NeurIPS-tut-LLM-watermark-part-2.pdf differ diff --git a/index.html b/index.html index fecb0bc..c972fd7 100644 --- a/index.html +++ b/index.html @@ -187,13 +187,13 @@
Presenter: Xuandong Zhao
This section provides the background for the tutorial, presenting the challenges posed by machine-written text and the potential ethical issues arising from Large Language Models (LLMs). We will introduce two primary approaches to addressing these issues: post-hoc detection and watermarking methods.
Presenter: Xuandong Zhao, Yu-Xiang Wang
We delve into the process and evolution of watermarking for natural languages. We further explore watermarking methods specifically designed for Large Language Models. We will also cover the theoretical analysis of each watermarking method.
@@ -249,6 +249,12 @@