Zero is Not Hero Yet: Benchmarking Zero-Shot Performance of LLMs for Financial Tasks
This work addresses the feasibility of using generative LLMs for financial domain tasks, showing incremental improvements but noting practical limitations like annotation time.
The paper investigated the effectiveness of zero-shot large language models (LLMs) like ChatGPT for financial tasks, finding that while ChatGPT performs well without labeled data, fine-tuned models generally outperform it, with specific performance gaps highlighted.
Recently large language models (LLMs) like ChatGPT have shown impressive performance on many natural language processing tasks with zero-shot. In this paper, we investigate the effectiveness of zero-shot LLMs in the financial domain. We compare the performance of ChatGPT along with some open-source generative LLMs in zero-shot mode with RoBERTa fine-tuned on annotated data. We address three inter-related research questions on data annotation, performance gaps, and the feasibility of employing generative models in the finance domain. Our findings demonstrate that ChatGPT performs well even without labeled data but fine-tuned models generally outperform it. Our research also highlights how annotating with generative models can be time-intensive. Our codebase is publicly available on GitHub under CC BY-NC 4.0 license.