Summary of Efficacy Of Large Language Models in Systematic Reviews, by Aaditya Shah and Shridhar Mehendale and Siddha Kanthi
Efficacy of Large Language Models in Systematic Reviews
by Aaditya Shah, Shridhar Mehendale, Siddha Kanthi
First submitted to arxiv on: 3 Aug 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Machine Learning (cs.LG)
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 The study assesses the performance of Large Language Models (LLMs) in interpreting existing literature on Environmental, Social, and Governance (ESG) factors and financial performance. A systematic review is conducted on a corpus of ESG-focused papers to evaluate the accuracy of LLMs in replicating human-made classifications. The investigation compares two state-of-the-art LLMs, Meta AI’s Llama 3 8B and OpenAI’s GPT-4o, with a “Custom GPT” and a fine-tuned GPT-4o Mini model using the corpus as training data. The findings show that the fine-tuned GPT-4o Mini model outperforms the base LLMs by 28.3% on average in overall accuracy. The study’s results suggest promising applications for investors and agencies to leverage LLMs for summarizing complex evidence related to ESG investing, enabling quicker decision-making and a more efficient market. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper explores how computers can understand existing research about how companies’ environmental, social, and governance actions affect their finances. Researchers used special computer models called Large Language Models (LLMs) to see if they could summarize what other researchers wrote about this topic. They tested different LLMs on a big collection of papers to find out which one worked best. The results show that one of the models did really well at summarizing these papers, and it might be helpful for investors or companies trying to make decisions based on this research. |
Keywords
» Artificial intelligence » Gpt » Llama
