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.
When the financial liability is derecognized, this portion should be reclassified from OCI to profit or loss
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.