Update README.md

README.md

@@ -19,32 +19,13 @@ tools:
 ---
 # Rebuttal-RM 🏅 
 ## Introduction 
-Rebuttal-RM is an open-source scorer that emulates human reviewers when judging an author’s reply to a peer-review comment.
-
-#### 1.1 Purpose  
-* Produce four rubric-aligned 0-to-10 scores  
-  1. Attitude (tone & professionalism)  
-  2. Clarity (logical flow)  
-  3. Persuasiveness (strength of evidence)  
-  4. Constructiveness (actionable improvement)  
-* Return a short textual explanation for transparency.  
-* Serve both as (i) a public benchmark and (ii) the reward signal for RebuttalAgent RL.
-
-#### 1.2 Model I/O  
-Input : {relevant paper chunks} + {full review Ri} + {target comment} + {candidate response}
-Output: {
-"score": {Attitude, Clarity, Persuasiveness, Constructiveness},
-"explanation": "..."
-}
-
-#### 1.3 Model Recipe  
-* Backbone: **Qwen-3-8B-Chat**  
-* Supervised fine-tuning on the RM_Bench dataset  
- 
+ **Rebuttal-RM** is a scoring model trained to automatically assess author responses in light of the target comment and its supporting context, with the explicit goal of matching human‐reviewer preferences.  The reward model, denoted **GRM**, receives as input the retrieved evidence chunks **CE**, the current review **R_i**, the target comment **target**, and a candidate reply **response**; it returns a vector of rubric-aligned scores *s* together with an explanatory rationale **e**.  Formally,
 
-The resulting model offers reproducible, high-fidelity evaluation 
+$$
+(s,e)\;=\;\mathrm{GRM}\!\bigl(\,\sum_{p_j\in\text{CE}} p_j,\; R_i,\; c_{\text{target}},\; r_{\text{response}}\bigr).
+$$
 
----
+To obtain a robust evaluator we curate **102 K** training instances drawn from three sources: (i) 12 000 original author rebuttals that serve as a human baseline, (ii) GPT-4.1–refined answers representing an upper quality bound, and (iii) diverse model-generated replies (e.g., Qwen-2.5-3B, Claude-3.5) to broaden stylistic coverage.  Using **Qwen-3-8B** as the backbone, we fine-tune on this corpus to yield the final Rebuttal-RM.  As reported in Table 1, Rebuttal-RM achieves the strongest agreement with expert annotators, posting an average correlation of 0.812 and outperforming GPT-4.1 and DeepSeek-R1 by 9.0 % and 15.2 %, respectively.## 2 Performance (agreement with human ratings)
 
 ## 2 Performance (agreement with human ratings)