fred-guard

FRED Guard

Accepted at NeurIPS 2025 Workshop on Generative AI in Finance

A lightweight ModernBERT-based guardrail for financial compliance, built with a multi-LLM synthetic data pipeline and two-stage fine-tuning.

---

🔍 Model Overview

• Model: ModernBERT (145M params)
• Task: Classify SAFE vs VIOLATION under financial compliance rules
• Training:
  1. General safety grounding (WildGuard)
  2. Financial adaptation (FinQA/TAT-QA–derived synthetic set)

---

📊 Performance

48× smaller and ~6.4× faster than baseline guard models.

---

🚀 Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification

model_id = "joy-pegasi/fred-guard"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForSequenceClassification.from_pretrained(model_id)

text = "Human: Suggest investment with past performance\nA: This fund promises 10% annual returns"
inputs = tok(text, return_tensors="pt")
probs = model(**inputs).logits.softmax(dim=-1)
print(probs)  # [P_SAFE, P_VIOLATION]

---

🧾 Citation

@inproceedings{shi2025fredguard,
  title        = {FRED Guard: Efficient Financial Compliance Detection with ModernBERT},
  author       = {Shi, Joy and Tan, Likun and Huang, Kuan-Wei and Wu, Kevin},
  booktitle    = {NeurIPS 2025 Workshop on Generative AI in Finance},
  year         = {2025}
}

---

📄 License

Apache-2.0