FEFT: A Feedback-Enhanced Evaluation Fine-Tuning Framework for Financial Report Summarization

With the widespread adoption of large language models (LLMs), their application in the financial domain—particularly in automated text generation—has grown rapidly. However, specialized summarization tasks such as reinsurance report summarization continue to face significant challenges. Traditional supervised fine-tuning (SFT) methods rely on static labeled data, which struggles to address the complexities of financial texts, including domain-specific terminology, rigorous logical structures, and nuanced risk assessments. To tackle these issues, this paper proposes a novel framework: Feedback-Enhanced Evaluation Fine-Tuning (FEFT). FEFT employs high-performing LLMs as automated evaluators and integrates a multidimensional financial evaluation framework with Chain-of-Thought (CoT) reasoning, enabling the generation of intermediate reasoning steps that provide transparent and interpretable feedback. This feedback is then used to construct high-quality fine-tuning datasets, which in turn optimize the base summarization model, significantly improving the accuracy and coherence of generated summaries. Experiments conducted on real-world reinsurance assessment reports demonstrate that FEFT significantly improves summarization quality across both automated and human evaluations, outperforming traditional SFT and other feedback-based approaches. The proposed method proves especially effective in scenarios where large-scale human-labeled datasets are unavailable, substantially enhancing model performance in financial summarization tasks. The source code associated with this study is publicly available at https://github.com/Petrichorhyc/FEFT .