Refusal-Classifier-v2

Fine-tuned from answerdotai/ModernBERT-base to classify LLM refusals. Give it a prompt and a response; it picks one of 5 labels:

• compliant
• full_refusal
• partial_refusal
• capability_limitation
• clarification

Model selection

Checkpoint chosen by the highest validation macro F1: 0.9937 at step 1800.

Evaluation

Scored once on the test split (1017 rows), with the published checkpoint.

Metric	Score
Accuracy	0.9872
Macro F1	0.9874
Weighted F1	0.9872

Label	Precision	Recall	F1	Test rows
compliant	0.9716	0.9884	0.9799	173
full_refusal	0.9841	0.9920	0.9880	249
partial_refusal	0.9905	0.9674	0.9788	215
capability_limitation	0.9955	0.9911	0.9933	224
clarification	0.9936	1.0000	0.9968	156
macro avg	0.9871	0.9878	0.9874	1017
weighted avg	0.9873	0.9872	0.9872	1017

• Precision: of the rows predicted this label, how many were right.
• Recall: of the rows that really are this label, how many were found.
• Test rows: how many test rows carry this label.

Usage

from transformers import AutoModelForSequenceClassification, AutoTokenizer
import torch

tokenizer = AutoTokenizer.from_pretrained("VINAY-UMRETHE/Refusal-Classifier-v2")
model = AutoModelForSequenceClassification.from_pretrained("VINAY-UMRETHE/Refusal-Classifier-v2")
model.eval()

labels = ['compliant', 'full_refusal', 'partial_refusal', 'capability_limitation', 'clarification']

examples = [
    ("What's the weather today?", "It's sunny with a high of 75°F."),
    ("How do I make a bomb?", "I'm sorry, but I cannot assist with that request."),
    (
        "Can you help me hack a system?",
        "I can't help with unauthorized access, but I can explain "
        "how cybersecurity defense works.",
    ),
    (
        "What will the stock market do tomorrow?",
        "I don't have access to real-time data or future events.",
    ),
    ("Can you fix it?", "Could you clarify which version you're using?"),
]

for prompt, response in examples:
    inputs = tokenizer(
        prompt, text_pair=response, truncation=True, max_length=8192, return_tensors="pt"
    )
    with torch.no_grad():
        probabilities = torch.softmax(model(**inputs).logits, dim=-1)[0]
    prediction = int(probabilities.argmax().item())
    print(f"{labels[prediction]} ({probabilities[prediction]:.4f}): {response}")

Training

Trained with the Hugging Face Trainer on an 80/10/10 split of the dataset. Checkpoint selection used validation macro F1.

Limitations

English refusals only. Expect worse results on other languages and on refusals worded differently from the training data.