CatMemo at the FinLLM Challenge Task: Fine-Tuning Large Language Models using Data Fusion in Financial Applications
By Yupeng Cao, Zhiyuan Yao, Zhi Chen, Zhiyang Deng
Rating
1299
Battle Count: 80
Relevance
7/10
The paper addresses financial text classification, summarization, and single stock trading, which are relevant to quantitative trading, but shows limited success in the trading task
Implementation Complexity
6/10
The implementation involves fine-tuning LLMs with PEFT and LoRA, which requires moderate technical expertise
Reproducibility
3/5
The paper provides details on the models and techniques used, but full reproducibility may require additional implementation details
About this paper
Methodology: Fine-tuning with Data Fusion. Problem types: Classification, Text Summarization, Time Series Forecasting.
The interactive Everscope explorer (charts, battles, favorites) loads below.