AI 中文总结
本研究通过秩16的LoRA适配Qwen3.5-4B，在22,000示例上训练，并在600示例基准上验证，证明紧凑金融领域适配在匹配提示下能显著提升任务性能，超越仅格式学习。
AI 中文摘要
FinVector-Market-4B在包含22,000个示例的语料库上，采用秩为16的LoRA对Qwen/Qwen3.5-4B进行适配，以处理结构化金融任务。我们在相同的600个示例基准上，在隐式和显式JSON模式契约下评估基础模型和适配模型。仅提供模式即可将基础模型的JSON有效性从0%提升至91.3%。在匹配的显式提示下，冻结分数从14.7%提升至40.0%（FinQA答案精确匹配），从48.0%提升至82.7%（计算器表达式正确性），从20.1%提升至89.5%（场景分支标签一致性），从52.4%提升至87.2%（蕴含方向一致性）。事后策略评分审计显示，报告的宏F1下降反映了标签集的变化；使用相同的三个目标类别，基础模型为77.4%，适配器为83.1%。备案重叠和计算器目标不一致性限制了基准的泛化主张。结果表明，在匹配提示下，紧凑的金融领域适配可以产生超越输出格式学习的实质性任务特定收益，且收益受限于所评估的任务分布和提示契约。
英文摘要
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.
Comments13 pages, 3 figures, 8 tables
