Despite continuous advancements in the capabilities of large language models (LLMs), numerical reasoning remains a challenging area. Techniques like chain-of-thought prompting, tree-of-thought prompting, and program-of-thought prompting guide LLMs through intermediate reasoning steps. Although in-context learning with few-shot prompting has improved performance, LLMs still lag behind state-of-the-art models on financial numerical reasoning datasets such as FinQA and ConvFinQA. In this work, we introduce FINDER, a novel two-step framework, to enhance LLMs' capabilities in financial numerical reasoning. The first step utilizes a generative retriever to extract relevant facts from unstructured data, including both text and tables. This is followed by context-aware Program of Thought prompting with dynamic selection of in-context examples. Our model FINDER achieves a new state-of-the-art performance on both the FinQA and ConvFinQA datasets, surpassing previous benchmarks with execution accuracy improvements of 5.98% and 4.05%, respectively.
@article{arxiv.2510.13157,
title = {Program of Thoughts for Financial Reasoning: Leveraging Dynamic In-Context Examples and Generative Retrieval},
author = {Subhendu Khatuya and Shashwat Naidu and Pawan Goyal and Niloy Ganguly},
journal= {arXiv preprint arXiv:2510.13157},
year = {2025}
}
Comments
This work has been accepted for publication in the Main Conference of the Empirical Methods in Natural Language Processing (EMNLP) 2025