Search papers, labs, and topics across Lattice.
Affiliation:
3
0
4
1
Financial time series data can boost classification accuracy in monetary-policy stance detection, achieving over 70% F1 score with minimal human annotations.
LLM-generated explanations, despite being high-quality, can actually hurt decision-making by increasing confidence without improving accuracy and even masking model failures.
Finetuning LLMs on news sentiment boosts aluminum price forecasting, especially when markets are most turbulent.