Add metadata and improve model card

README.md

@@ -1,7 +1,22 @@
+---
+library_name: transformers
+pipeline_tag: text-generation
+base_model: Qwen/Qwen3-8B
+tags:
+- reward-modeling
+- rlhf
+- rubric-arm
+- post-training
+---
+
 # OpenRubrics/RubricRM-8B-Rubric-v2
 
-This is a 8B RubricARM-Rubric model, finetuned from [Qwen3/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B). 
-See our [paper](https://arxiv.org/abs/2602.01511) for more details.
+This is a 8B RubricARM-Rubric model, finetuned from [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B). 
+
+## Model Description
+Rubric-ARM is a framework introduced in the paper [Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training](https://huggingface.co/papers/2602.01511). Standard reward models typically predict scalar scores that fail to capture the multifaceted nature of response quality in non-verifiable domains, such as creative writing or open-ended instruction following. 
+
+This specific checkpoint serves as the **rubric generator**, which is jointly optimized with a judge using reinforcement learning from preference feedback. It is designed to extract a set of rubric-style instructions from a user's request to be used as evaluation criteria.
 
 ## Usage
 ```python
@@ -16,29 +31,52 @@ To evaluate the model, please use the following format to build up message.
 
 ```python
 RUBRIC_PROMPT_TEMPLATE = (
-    "Your task is to extract a set of rubric-style instructions from a user's request.\n"
-    "These rubrics will be used as evaluation criteria to check if a response fully meets the request.\n"
-    "Every rubric item must be a universal principle. If any rubric still contains topic-specific references (e.g., names, places, myths, numbers, historical facts), it is automatically invalid.\n"
-    "\n"
-    "- **Two Distinct Categories:**\n"
-    "  - [Hard Rule]: Derived strictly from explicit requirements stated in the <request> (format, length, structure, forbidden/required elements, etc.).\n"
-    "  - [Principle]: Derived by abstracting any concrete cues into domain-agnostic quality criteria (e.g., clarity, correctness, sound reasoning, pedagogy).\n"
-    "\n"
-    "- **Comprehensiveness:**\n"
-    "  The rubric must cover all critical aspects implied by the request and examples, including explicit requirements and implicit quality standards.\n"
-    "\n"
-    "- **Conciseness & Uniqueness:**\n"
-    "  Each rubric must capture a distinct evaluation criterion. Overlapping or redundant criteria must be merged into a single rubric. Wording must be precise and free of repetition.\n"
-    "\n"
-    "- **Format Requirements:**\n"
-    "  - Use a numbered list.\n"
-    "  - Each item starts with \"The response\" phrased in third person.\n"
-    "  - Append [Hard Rule] or [Principle] at the end of each item.\n"
-    "  - Do not include reasoning, explanations, or examples in the final output—only the rubrics.\n"
-    "\n"
-    "Here is the request:\n"
-    "{prompt}\n"
-    "\n"
+    "Your task is to extract a set of rubric-style instructions from a user's request.
+"
+    "These rubrics will be used as evaluation criteria to check if a response fully meets the request.
+"
+    "Every rubric item must be a universal principle. If any rubric still contains topic-specific references (e.g., names, places, myths, numbers, historical facts), it is automatically invalid.
+"
+    "
+"
+    "- **Two Distinct Categories:**
+"
+    "  - [Hard Rule]: Derived strictly from explicit requirements stated in the <request> (format, length, structure, forbidden/required elements, etc.).
+"
+    "  - [Principle]: Derived by abstracting any concrete cues into domain-agnostic quality criteria (e.g., clarity, correctness, sound reasoning, pedagogy).
+"
+    "
+"
+    "- **Comprehensiveness:**
+"
+    "  The rubric must cover all critical aspects implied by the request and examples, including explicit requirements and implicit quality standards.
+"
+    "
+"
+    "- **Conciseness & Uniqueness:**
+"
+    "  Each rubric must capture a distinct evaluation criterion. Overlapping or redundant criteria must be merged into a single rubric. Wording must be precise and free of repetition.
+"
+    "
+"
+    "- **Format Requirements:**
+"
+    "  - Use a numbered list.
+"
+    "  - Each item starts with \"The response\" phrased in third person.
+"
+    "  - Append [Hard Rule] or [Principle] at the end of each item.
+"
+    "  - Do not include reasoning, explanations, or examples in the final output—only the rubrics.
+"
+    "
+"
+    "Here is the request:
+"
+    "{prompt}
+"
+    "
+"
     "Please generate the rubrics for the above request."
 )
 
@@ -63,9 +101,11 @@ message = tok.apply_chat_template(
 ```
 
 
+## Citation
+
 If you find our work helpful, please consider citing our paper:
 
-```
+```bibtex
 @misc{xu2026alternating,
       title={Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training}, 
       author={Ran Xu and Tianci Liu and Zihan Dong and Tony You and Ilgee Hong and Carl Yang and Linjun Zhang and Tao Zhao and Haoyu Wang},