Summary of Fine-tuning Smaller Language Models For Question Answering Over Financial Documents, by Karmvir Singh Phogat et al.
Fine-tuning Smaller Language Models for Question Answering over Financial Documents
by Karmvir Singh Phogat, Sai Akhil Puranam, Sridhar Dasaratha, Chetan Harsha, Shashishekar Ramakrishna
First submitted to arxiv on: 22 Aug 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Systems and Control (eess.SY)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This research explores a paradigm where smaller language models are fine-tuned with exemplars crafted by a larger teacher model, enabling them to acquire substantial reasoning abilities. In this study, the authors apply this approach to the financial domain, focusing on answering questions that require multi-hop numerical reasoning over financial texts. They assess the performance of several smaller models fine-tuned to generate programs encoding required financial calculations and find that these models approach the performance of the teacher model. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research looks at how small language models can get better at making sense of financial data by learning from larger models. The goal is to help computers answer questions about money in a way that makes sense, like figuring out how much something costs based on past prices and trends. The study shows that these smaller models can do almost as well as the bigger ones when it comes to understanding and crunching numbers. |
Keywords
» Artificial intelligence » Teacher model
