Merge branch 'main' of https://huggingface.co/spaces/allenai/reward-bench

app.py

@@ -350,7 +350,7 @@ Warning, refusals, XSTest, and donotanswer datasets have sensitive content.""")
         with gr.Accordion("📚 Citation", open=False):
             citation_button = gr.Textbox(
                 value=r"""@misc{RewardBench,
-    title={RewardBench: Benchmarking Reward Models},
+    title={RewardBench: Evaluating Reward Models},
     author={Lambert, Nathan and Pyatkin, Valentina and Morrison, Jacob and Miranda, LJ and Lin, Bill Yuchen and Chandu, Khyathi and Dziri, Nouha and Kumar, Sachin and Zick, Tom and Choi, Yejin and Smith, Noah A. and Hajishirzi, Hannaneh},
     year={2024},
     howpublished={\url{https://huggingface.co/spaces/allenai/reward-bench}

src/md.py

@@ -92,5 +92,5 @@ For more details, see the [dataset](https://huggingface.co/datasets/allenai/rewa
 TOP_TEXT = """
 # RewardBench: Evaluating Reward Models
 ### Evaluating the capabilities, safety, and pitfalls of reward models
-[Code](https://github.com/allenai/reward-bench) | [Eval. Dataset](https://huggingface.co/datasets/allenai/reward-bench) | [Classic Test Sets](https://huggingface.co/datasets/allenai/pref-test-sets) | [Results](https://huggingface.co/datasets/allenai/reward-bench-results) | Paper (coming soon)
+[Code](https://github.com/allenai/reward-bench) | [Eval. Dataset](https://huggingface.co/datasets/allenai/reward-bench) | [Prior Test Sets](https://huggingface.co/datasets/allenai/pref-test-sets) | [Results](https://huggingface.co/datasets/allenai/reward-bench-results) | Paper (coming soon)
 """