Hindsight Preference Optimization lets a 4B model outperform a 235B model on S&P 500 advisory accuracy and quality by generating DPO preference pairs from outcome-based LLM judgments on time series predictions.
Huang, Nan Xu, Sheng Zhang, Hoifung Poon, and Muhao Chen
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Hindsight Preference Optimization for Financial Time Series Advisory
Hindsight Preference Optimization lets a 4B model outperform a 235B model on S&P 500 advisory accuracy and quality by generating DPO preference pairs from outcome-based LLM judgments on time series predictions.