Demystifying Domain-adaptive Post-training for Financial LLMs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917030907609088 |
|---|---|
| author | Ke, Zixuan Ming, Yifei Nguyen, Xuan-Phi Xiong, Caiming Joty, Shafiq |
| author_facet | Ke, Zixuan Ming, Yifei Nguyen, Xuan-Phi Xiong, Caiming Joty, Shafiq |
| contents | Domain-adaptive post-training of large language models (LLMs) has emerged as a promising approach for specialized domains such as medicine and finance. However, significant challenges remain in identifying optimal adaptation criteria and training strategies across varying data and model configurations. To address these challenges, we introduce FINDAP, a systematic and fine-grained investigation into domain-adaptive post-training of LLMs for the finance domain. Our approach consists of four key components: FinCap, which defines the core capabilities required for the target domain; FinRec, an effective training recipe that jointly optimizes continual pre-training and instruction-following, along with a novel preference data distillation method leveraging process signals from a generative reward model; FinTrain, a curated set of training datasets supporting FinRec; and FinEval, a comprehensive evaluation suite aligned with FinCap. The resulting model, Llama-Fin, achieves state-of-the-art performance across a wide range of financial tasks. Our analysis also highlights how each post-training stage contributes to distinct capabilities, uncovering specific challenges and effective solutions, providing valuable insights for domain adaptation of LLMs |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_04961 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Demystifying Domain-adaptive Post-training for Financial LLMs Ke, Zixuan Ming, Yifei Nguyen, Xuan-Phi Xiong, Caiming Joty, Shafiq Computation and Language Artificial Intelligence Computational Engineering, Finance, and Science Machine Learning Domain-adaptive post-training of large language models (LLMs) has emerged as a promising approach for specialized domains such as medicine and finance. However, significant challenges remain in identifying optimal adaptation criteria and training strategies across varying data and model configurations. To address these challenges, we introduce FINDAP, a systematic and fine-grained investigation into domain-adaptive post-training of LLMs for the finance domain. Our approach consists of four key components: FinCap, which defines the core capabilities required for the target domain; FinRec, an effective training recipe that jointly optimizes continual pre-training and instruction-following, along with a novel preference data distillation method leveraging process signals from a generative reward model; FinTrain, a curated set of training datasets supporting FinRec; and FinEval, a comprehensive evaluation suite aligned with FinCap. The resulting model, Llama-Fin, achieves state-of-the-art performance across a wide range of financial tasks. Our analysis also highlights how each post-training stage contributes to distinct capabilities, uncovering specific challenges and effective solutions, providing valuable insights for domain adaptation of LLMs |
| title | Demystifying Domain-adaptive Post-training for Financial LLMs |
| topic | Computation and Language Artificial Intelligence Computational Engineering, Finance, and Science Machine Learning |
| url | https://arxiv.org/abs/2501.04961 |