UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models
This provides a robust framework for assessing LLM performance and user satisfaction in the financial domain, though it is incremental as it builds on existing benchmarking methods.
The paper tackled the problem of evaluating large language models (LLMs) on complex real-world financial tasks by introducing the UCFE benchmark, which showed a Pearson correlation coefficient of 0.78 between benchmark scores and human preferences, confirming its effectiveness.
This paper introduces the UCFE: User-Centric Financial Expertise benchmark, an innovative framework designed to evaluate the ability of large language models (LLMs) to handle complex real-world financial tasks. UCFE benchmark adopts a hybrid approach that combines human expert evaluations with dynamic, task-specific interactions to simulate the complexities of evolving financial scenarios. Firstly, we conducted a user study involving 804 participants, collecting their feedback on financial tasks. Secondly, based on this feedback, we created our dataset that encompasses a wide range of user intents and interactions. This dataset serves as the foundation for benchmarking 11 LLMs services using the LLM-as-Judge methodology. Our results show a significant alignment between benchmark scores and human preferences, with a Pearson correlation coefficient of 0.78, confirming the effectiveness of the UCFE dataset and our evaluation approach. UCFE benchmark not only reveals the potential of LLMs in the financial domain but also provides a robust framework for assessing their performance and user satisfaction.