A preference-optimized LLM for financial sentiment beats supervised fine-tuning on a combined benchmark and, via a softmax-based score, appears to drive a profitable long-short portfolio in a backtest.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
FinDPO: Financial Sentiment Analysis for Algorithmic Trading through Preference Optimization of LLMs
A preference-optimized LLM for financial sentiment beats supervised fine-tuning on a combined benchmark and, via a softmax-based score, appears to drive a profitable long-short portfolio in a backtest.