Upload README.md with huggingface_hub

README.md

@@ -11,7 +11,7 @@ tags:
 
 # Binary-Think-RM-3B
 
-Binary-Think-RM-3B is a generative reward model with long-horizon reasoning capabilities, introduced in the paper [Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models](https://arxiv.org/abs/2505.16265).
+Binary-Think-RM-3B is a generative reward model with long-horizon reasoning capabilities, introduced in the paper [Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models](https://openreview.net/pdf?id=UfQAFbP6xq).
 
 This model is fine-tuned from [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) using a two-stage training process: (1) reasoning-oriented supervised fine-tuning (SFT) using [ilgee/hs2-naive-reasoning-binary-max](https://huggingface.co/datasets/ilgee/hs2-naive-reasoning-binary-max) and (2) reinforcement learning with verifiable rewards (RLVR) using a prompt part of [ilgee/hs2-naive-reasoning-binary-max](https://huggingface.co/datasets/ilgee/hs2-naive-reasoning-binary-max).
 
@@ -76,7 +76,7 @@ message = tokenizer.apply_chat_template(
 
 ## Performance
 
-For detailed performance metrics on RewardBench, RM-Bench, HelpSteer2-Preference, and HelpSteer3-Preference, please refer to Tables 5, 6, and 7 in the paper: [Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models](https://arxiv.org/abs/2505.16265)
+For detailed performance metrics on RewardBench, RM-Bench, HelpSteer2-Preference, and HelpSteer3-Preference, please refer to Tables 5, 6, and 7 in the paper: [Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models](https://openreview.net/pdf?id=UfQAFbP6xq)
 
 ## Citation