FRED: Financial Retrieval-Enhanced Detection and Editing of Hallucinations in Language Models

TL;DR

This paper introduces FRED, a method for detecting and editing hallucinated, factually incorrect content in financial language models, improving their reliability and trustworthiness in high-stakes domains.

Contribution

It presents a novel framework for detecting and editing hallucinations in language models using a domain-specific error taxonomy and synthetic dataset creation.

Findings

Phi-4 model improves detection F1 score by 8% over OpenAI-o3.

Phi-4-mini maintains competitive performance with only 4 billion parameters.

The approach generalizes to enhance trustworthiness of language models beyond finance.

Abstract

Hallucinations in large language models pose a critical challenge for applications requiring factual reliability, particularly in high-stakes domains such as finance. This work presents an effective approach for detecting and editing factually incorrect content in model-generated responses based on the provided context. Given a user-defined domain-specific error taxonomy, we construct a synthetic dataset by inserting tagged errors into financial question-answering corpora and then fine-tune four language models, Phi-4, Phi-4-mini, Qwen3-4B, and Qwen3-14B, to detect and edit these factual inaccuracies. Our best-performing model, fine-tuned Phi-4, achieves an 8% improvement in binary F1 score and a 30% gain in overall detection performance compared to OpenAI-o3. Notably, our fine-tuned Phi-4-mini model, despite having only 4 billion parameters, maintains competitive performance with just a 2% drop in binary detection and a 0.1% decline in overall detection compared to OpenAI-o3. Our work provides a practical solution for detecting and editing factual inconsistencies in financial text generation while introducing a generalizable framework that can enhance the trustworthiness and alignment of large language models across diverse applications beyond finance. Our code and data are available at https://github.com/pegasi-ai/shield.