One More Question is Enough, Expert Question Decomposition (EQD) Model for Domain Quantitative Reasoning
This addresses the problem of complex quantitative reasoning in specialized fields like finance for users relying on LLMs, representing an incremental improvement over existing methods.
The paper tackles the challenge of domain-specific quantitative reasoning for large language models by proposing the Expert Question Decomposition (EQD) model, which improves question-answering performance by 0.6% to 10.5% across benchmarks in the financial domain.
Domain-specific quantitative reasoning remains a major challenge for large language models (LLMs), especially in fields requiring expert knowledge and complex question answering (QA). In this work, we propose Expert Question Decomposition (EQD), an approach designed to balance the use of domain knowledge with computational efficiency. EQD is built on a two-step fine-tuning framework and guided by a reward function that measures the effectiveness of generated sub-questions in improving QA outcomes. It requires only a few thousand training examples and a single A100 GPU for fine-tuning, with inference time comparable to zero-shot prompting. Beyond its efficiency, EQD outperforms state-of-the-art domain-tuned models and advanced prompting strategies. We evaluate EQD in the financial domain, characterized by specialized knowledge and complex quantitative reasoning, across four benchmark datasets. Our method consistently improves QA performance by 0.6% to 10.5% across different LLMs. Our analysis reveals an important insight: in domain-specific QA, a single supporting question often provides greater benefit than detailed guidance steps.