ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering
This work addresses the problem of advancing AI reasoning abilities in real-world financial applications, though it is incremental as it focuses on dataset creation and analysis rather than a new method.
The authors tackled the challenge of modeling complex numerical reasoning in finance by introducing ConvFinQA, a large-scale dataset for conversational question answering, which requires long-range reasoning paths and was tested with neural symbolic and prompting-based methods.
With the recent advance in large pre-trained language models, researchers have achieved record performances in NLP tasks that mostly focus on language pattern matching. The community is experiencing the shift of the challenge from how to model language to the imitation of complex reasoning abilities like human beings. In this work, we investigate the application domain of finance that involves real-world, complex numerical reasoning. We propose a new large-scale dataset, ConvFinQA, aiming to study the chain of numerical reasoning in conversational question answering. Our dataset poses great challenge in modeling long-range, complex numerical reasoning paths in real-world conversations. We conduct comprehensive experiments and analyses with both the neural symbolic methods and the prompting-based methods, to provide insights into the reasoning mechanisms of these two divisions. We believe our new dataset should serve as a valuable resource to push forward the exploration of real-world, complex reasoning tasks as the next research focus. Our dataset and code is publicly available at https://github.com/czyssrs/ConvFinQA.