arXiv：cs.CL· Alina Khaybullina·· 3 小时前AI 评分34
FinVector-Market-4B：LoRA 适配结构化金融任务的对照研究
FinVector-Market-4B: A Controlled Study of LoRA Adaptation for Structured Financial Tasks
AI 导读
FinVector-Market-4B 以 rank-16 LoRA 在 22,000 条语料上适配 Qwen3.5-4B，并在同一 600 例基准上对比基座与适配模型。
正文
Abstract:FinVector-Market-4B adapts Qwen/Qwen3.5-4B with rank-16 LoRA on a 22,000-example corpus for structured financial tasks. We evaluate the base and adapted models on the same 600-example benchmark under implicit and explicit JSON-schema contracts. Supplying the schema alone raises base-model JSON validity from 0% to 91.3%. Under matched explicit prompting, the frozen scores improve from 14.7% to 40.0% for FinQA answer exact match, from 48.0% to 82.7% for calculator-expression correctness, from 20.1% to 89.5% for scenario branch-label agreement, and from 52.4% to 87.2% for implication-direction agreement. A post-hoc policy-scoring audit shows that the reported macro-F1 decline reflects a changing label set; using the same three target classes gives 77.4% for the base and 83.1% for the adapter. Filing overlap and calculator-target inconsistencies qualify the benchmark's generalization claims. The results show that compact financial domain adaptation can produce substantial task-specific gains beyond output-format learning under matched prompting, with gains bounded by the evaluated task distribution and prompt contract.
| Comments: | 13 pages, 3 figures, 8 tables |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); General Finance (q-fin.GN) |
| Cite as: | arXiv:2610.08882 [cs.LG] |
| (or arXiv:2610.08882v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.08882 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Alina Khaybullina [view email]
[v1]
Tue, 6 Oct 2026 10:46:58 UTC (567 KB)
来源：arXiv：cs.CL · arxiv.org