A survey that organizes recent LLM-in-finance research into four framework categories and summarizes the reported methods, datasets, and performance of about 30 systems.
Exploring LLM Cryptocurrency Trading Through Fact-Subjectivity Aware Reasoning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
While many studies show that more advanced LLMs excel in tasks such as mathematics and coding, we observe that in cryptocurrency trading, stronger LLMs sometimes underperform compared to weaker ones. To investigate this counterintuitive phenomenon, we examine how LLMs reason when making trading decisions. Our findings reveal that (1) stronger LLMs show a preference for factual information over subjectivity; (2) separating the reasoning process into factual and subjective components leads to higher profits. Building on these insights, we propose a multi-agent framework, FS-ReasoningAgent, which enables LLMs to recognize and learn from both factual and subjective reasoning. Extensive experiments demonstrate that this fine-grained reasoning approach enhances LLM trading performance in cryptocurrency markets, yielding profit improvements of 7\% in BTC, 2\% in ETH, and 10\% in SOL. Additionally, an ablation study reveals that relying on subjective news generates higher returns in bull markets, while focusing on factual information yields better results in bear markets. Code is available at https://github.com/Persdre/FS-ReasoningAgent.
fields
q-fin.GN 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Integrating Large Language Models in Financial Investments and Market Analysis: A Survey
A survey that organizes recent LLM-in-finance research into four framework categories and summarizes the reported methods, datasets, and performance of about 30 systems.