FEVO applies continued pretraining, supervised fine-tuning, and reinforcement learning to a 32B model, claiming state-of-the-art financial benchmark scores, but the evaluation appears contaminated by training data.
If the hedged forecast transaction ultimately occurs, these gains or losses will be reclassified to profit or loss in the future
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
FEVO: Financial Knowledge Expansion and Reasoning Evolution for Large Language Models
FEVO applies continued pretraining, supervised fine-tuning, and reinforcement learning to a 32B model, claiming state-of-the-art financial benchmark scores, but the evaluation appears contaminated by training data.