Update the numbers to reflect the LoRA with json object as output format (as opposed to plain text, which was for a previous version).

query_clarification/README.md

@@ -117,7 +117,7 @@ The evaluation uses a test set containing:
 
 | Model | Underspecified (80) | CLEAR - random (150) | CLEAR - hard (50) | Overall Accuracy |
 |-------|---------------------|----------------------|-------------------|------------------|
-| Granite-4.0-micro LoRA | 81.25% | 100% | 86% | **92.14%** |
+| Granite-4.0-micro LoRA | 76.25% | 99.33% | 80% | **89.3%** |
 
 **OOB models (prompted, zero-shot):**
 
@@ -127,17 +127,17 @@ The evaluation uses a test set containing:
 | GPT 4o | 60% | 85.3% | 48% | 71.42% |
 | Granite-4.0-micro | 97.5% | 5.3% | 0% | 30.71% |
 
-The LoRA achieves significantly higher overall accuracy due to its ability to correctly identify clear queries, while prompted models tend to over-clarify.
+The LoRA achieves higher overall accuracy due to its ability to correctly identify clear queries, while prompted models tend to over-clarify.
 
 ### Clarification Quality Results
 
-For queries correctly identified as underspecified, we measure the quality of generated clarification requests using an LLM judge (Llama-3.3-70b). The numbers in parentheses indicate how many of the 80 underspecified records each model correctly identified and generated clarifications for—quality metrics are measured only on those data points.
+For queries identified as underspecified, we measure the quality of generated clarification requests using an LLM judge (Llama-3.3-70b). The numbers in parentheses indicate how many of the 80 underspecified records each model correctly identified and generated clarifications for—quality metrics are measured only on those data points.
 
 **Trained LoRA:**
 
 | Model | Precision | Recall | F1 |
 |-------|-----------|--------|-----|
-| Granite-4.0-micro LoRA (65/80) | 88.4% | 78.3% | 83.0% |
+| Granite-4.0-micro LoRA (61/80) | 90.4% | 80.1% | 84.9% |
 
 **OOB models (prompted, zero-shot):**
 
@@ -161,7 +161,7 @@ The LoRA achieves clarification quality close to GPT-4o while maintaining much b
 | **Target Modules** | q_proj, k_proj, v_proj, o_proj, input_linear, output_linear |
 
 **Infrastructure:**
-We trained the query clarification granite-4.0-micro LoRA adapter on IBM's Vela cluster using 8 A100 GPUs.
+We trained the query clarification granite-4.0-micro LoRA adapter on IBM's Vela cluster using 8 H100 GPUs.
 
 **Ethical Considerations & Limitations:**
 The model's outputs are not guaranteed to be factually accurate or complete. All outputs should be independently validated before use in decision-making or downstream applications. The model has been trained and evaluated on English data only.