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

arXiv: https://arxiv.org/abs/2507.20930 · HTML: https://mlsanity.com/paper/2507.20930/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 22 references that are in the map.
- First posted on arXiv 28 Jul 2025.

## Builds on (most cited first, 15 of 15)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [FinQA: A Dataset of Numerical Reasoning over Financial Data](https://mlsanity.com/paper/2109.00122/) (2021)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021)
- [Fine-grained Hallucination Detection and Editing for Language Models](https://mlsanity.com/paper/2401.06855/) (2024)
- [RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2407.11005/) (2024)
- [ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability](https://mlsanity.com/paper/2410.11414/) (2024)
- [FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasets](https://mlsanity.com/paper/2310.04793/) (2023)
- [LettuceDetect: A Hallucination Detection Framework for RAG Applications](https://mlsanity.com/paper/2502.17125/) (2025)
- [GLIDER: Grading LLM Interactions and Decisions using Explainable Ranking](https://mlsanity.com/paper/2412.14140/) (2024)
- [GenAudit: Fixing Factual Errors in Language Model Outputs with Evidence](https://mlsanity.com/paper/2402.12566/) (2024)
- [PFME: A Modular Approach for Fine-grained Hallucination Detection and Editing of Large Language Models](https://mlsanity.com/paper/2407.00488/) (2024)

## Built on by (most cited first, 6 of 6)

- [Agentic Trading: When LLM Agents Meet Financial Markets](https://mlsanity.com/paper/2605.19337/) (2026)
- [Neuro-Symbolic Financial Reasoning via Deterministic Fact Ledgers and Adversarial Low-Latency Hallucination Detector](https://mlsanity.com/paper/2603.04663/) (2026)
- [InterpDetect: Interpretable Signals for Detecting Hallucinations in Retrieval-Augmented Generation](https://mlsanity.com/paper/2510.21538/) (2025)
- [CausalGaze: Unveiling Hallucinations via Counterfactual Graph Intervention in Large Language Models](https://mlsanity.com/paper/2604.11087/) (2026)
- [Confidently Wrong: Detecting Hallucinations in Financial Question Answering from LLM Internal States](https://mlsanity.com/paper/2607.11414/) (2026)
- [CLAIR-Fin: An Adversarial Multi-Agent Framework for Claim-Level Verification and Adaptive Debate in Cross-Modal Financial QA](https://mlsanity.com/paper/2608.13706/) (2026)

## Abstract (arXiv)

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.