LLMs Meet Finance
A three-stage fine-tuning pipeline (SFT → DPO → synthetic-data RL) that adapts Qwen2.5 and DeepSeek-R1 to financial tasks on the Open FinLLM Leaderboard, with findings on cross-task transfer and data scaling laws in finance.
- from
- AI in Finance
- added
- 2026-10-10
- likes
- 0
similar
-
-
FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance, 2020 arxiv.org
Introduce a DRL library FinRL that facilitates beginners to expose themselves to quantitative finance and to develop their own stock trading strategies.
-
Advanced-Deep-Trading github.com
Experiments based on "Advances in financial machine learning" book.
-
-
FinRpt arxiv.org
Dataset, Evaluation System and LLM-based Multi-agent Framework for Equity Research Report Generation.
-
Hands-on LLMs: Train and Deploy a Real-time Financial Advisor github.com
Train and deploy a real-time financial advisor chatbot with Falcon 7B and CometLLM.
AI in Finance › LLMs: “A three-stage fine-tuning pipeline (SFT → DPO → synthetic-data RL) that adapts Qwen2.5 and DeepSeek-R1 to financial tasks on the Open FinLLM Leaderboard, with findings on cross-task transfer and data scaling laws in finance.”