Search papers, labs, and topics across Lattice.
The authors investigate the impact of data quality and difficulty on LLM performance in the finance domain. They introduce ODA-Fin-SFT-318k, a high-quality Chain-of-Thought dataset created via multi-stage distillation and verification, and ODA-Fin-RL-12k, a dataset curated for difficult but verifiable tasks. Experiments using SFT and RL pipelines demonstrate that high-quality CoT distillation improves the SFT foundation, while difficulty-aware sampling enhances RL generalization, leading to state-of-the-art performance on financial benchmarks with an 8B model.
Forget scaling laws, targeted data engineering—specifically multi-stage distillation and difficulty-aware sampling—allows an 8B model to outperform larger open-source financial LLMs.
Large Language Models (LLMs) have demonstrated strong general capabilities, yet their deployment in finance remains challenging due to dense domain-specific terminology, stringent numerical reasoning requirements, and low tolerance for factual errors. We conduct a controlled empirical study showing that in specialized vertical domains, performance is largely determined by the quality and difficulty/verifiability profile of post-training data. We introduce \textbf{ODA-Fin-SFT-318k}, constructed via multi-stage distillation and verification to produce high-quality Chain-of-Thought supervision, and \textbf{ODA-Fin-RL-12k}, curated for hard-but-verifiable tasks that balance reward precision and task diversity. Using standard SFT and RL pipelines, we show that high-quality CoT distillation establishes a robust foundation during SFT, while difficulty- and verifiability-aware sampling improves RL generalization. Evaluated on nine benchmarks spanning general financial tasks, sentiment analysis, and numerical reasoning, our ODA-Fin-RL-8B consistently surpasses open-source state-of-the-art (SOTA) financial LLMs of comparable size. We release our ODA-Fin-SFT-318k and ODA-Fin-RL-12k datasets, along with trained models to advance data-centric financial AI research.