Metraipolis › archive › dc_000e02e882b5
FinVector-Market-4B: A Controlled Study of LoRA Adaptation for Structured Financial Tasks — arXiv:2610.08882
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.08882
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T11:10:16.796Z
- SHA-256 of the archived text
330cd683738e02537be69d82a8ec177f2bbb7558d3a798ca95512abc24dbacf3- Stable URL of this page
https://metraipolis.com/documento/dc_000e02e882b5
How to cite
FinVector-Market-4B: A Controlled Study of LoRA Adaptation for Structured Financial Tasks — arXiv:2610.08882 — arXiv (en), https://arxiv.org/abs/2610.08882 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_000e02e882b5 (Metraipolis archive dc_000e02e882b5, sha256 330cd683738e02537be69d82a8ec177f2bbb7558d3a798ca95512abc24dbacf3)
BibTeX
@misc{dc000e02e882b5,
title = {FinVector-Market-4B: A Controlled Study of LoRA Adaptation for Structured Financial Tasks — arXiv:2610.08882},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.08882},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_000e02e882b5; sha256 330cd683738e02537be69d82a8ec177f2bbb7558d3a798ca95512abc24dbacf3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08882. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); General Finance (q-fin.GN). Pagina del lavoro: https://arxiv.org/abs/2610.08882 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T10:14:06.021Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).