add a paper about LLM-evaluation

paper_list/protein_pretraining.md

@@ -0,0 +1,5 @@
+# LLM-Evaluation
+
+## Papers
+
+- **How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks.** (2023-03), Xuanting Chen, Junjie Ye et al. [[pdf]](https://arxiv.org/abs/2303.00293)