Large language models (LLMs) show promise for natural language tasks but
struggle when applied directly to complex domains like finance. LLMs have
difficulty reasoning about and integrating all relevant information. We propose
a data-centric approach to enable LLMs to better handle financial tasks. Our
key insight is that rather than overloading the LLM with everything at once, it
is more effective to preprocess and pre-understand the data. We create a
financial LLM (FLLM) using multitask prompt-based finetuning to achieve data
pre-processing and pre-understanding. However, labeled data is scarce for each
task. To overcome manual annotation costs, we employ abductive augmentation
reasoning (AAR) to automatically generate training data by modifying the pseudo
labels from FLLM's own outputs. Experiments show our data-centric FLLM with AAR
substantially outperforms baseline financial LLMs designed for raw text,
achieving state-of-the-art on financial analysis and interpretation tasks. We
also open source a new benchmark for financial analysis and interpretation. Our
methodology provides a promising path to unlock LLMs' potential for complex
real-world domains.

通过数据中心的方法，我们提出了一种能够更好地处理金融任务的金融 LLM（FLLM）模型，通过多任务提示优化来对数据进行预处理和预理解，并通过推断增强推理（AAR）自动生成训练数据，实验结果表明，我们的数据中心 FLLM 模型显著优于基于原始文本的金融 LLMs，在金融分析和解释任务上达到了最新水平，我们还开源了一个新的金融分析和解释基准，这种方法为解锁 LLMs 在复杂现实领域的潜力提供了希望。