update link

constants.py

@@ -21,7 +21,7 @@ INTRODUCTION_TEXT= """
 > URIAL Bench tests the capacity of base LLMs for alignment without introducing the factors of fine-tuning (learning rate, data, etc.), which are hard to control for fair comparisons. 
 Specifically, we use [URIAL](https://github.com/Re-Align/URIAL/tree/main/run_scripts/mt-bench#run-urial-inference) to align a base LLM, and evaluate its performance on MT-Bench.
 
-- [🐑 URIAL](https://arxiv.org/abs/2312.01552) uses three constant examples to align BASE LLMs with in-context learning.
+- [🐑 URIAL](https://arxiv.org/abs/2312.01552) uses K=3 constant [examples](https://github.com/Re-Align/URIAL/blob/main/urial_prompts/inst_1k_v4.help.txt.md) to align BASE LLMs with in-context learning.
 - [📊 MT-Bench](https://huggingface.co/spaces/lmsys/mt-bench) is a small, curated benchmark with two turns of instruction following tasks in 10 domains.