Metraipolis › archive › dc_bcc9ea3eb5b7
FinReportBench: Measuring and Improving Institution-Grade Financial Report Generation — arXiv:2608.04374
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.04374
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:13:42.738Z
- SHA-256 of the archived text
0ae70d27a44f6f58c3c40c58e0a25d222096081aa9b07d051a2ae8d18d7f5633- Stable URL of this page
https://metraipolis.com/documento/dc_bcc9ea3eb5b7
How to cite
FinReportBench: Measuring and Improving Institution-Grade Financial Report Generation — arXiv:2608.04374 — arXiv (en), https://arxiv.org/abs/2608.04374 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bcc9ea3eb5b7 (Metraipolis archive dc_bcc9ea3eb5b7, sha256 0ae70d27a44f6f58c3c40c58e0a25d222096081aa9b07d051a2ae8d18d7f5633)
BibTeX
@misc{dcbcc9ea3eb5b7,
title = {FinReportBench: Measuring and Improving Institution-Grade Financial Report Generation — arXiv:2608.04374},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.04374},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bcc9ea3eb5b7; sha256 0ae70d27a44f6f58c3c40c58e0a25d222096081aa9b07d051a2ae8d18d7f5633},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04374. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models can produce fluent financial analysis, but fluency alone does not establish whether a report is suitable for institutional delivery. We introduce FinReportBench, an expert-grounded benchmark for measuring and improving institution-grade financial report generation. Expert review reveals recurring gaps in report identity, institutional components, source discipline, and visual delivery. We derive a 35-item rubric through expert partial orders, multimodal evidence, and audits of decision boundaries, covering deliverability, report identity, and institutional completeness. Starting from 10,000 balanced Chinese and English financial-research source records, we curate 244 bilingual tasks across three research objects and two input tiers. Each task separates the public query, reconstructed research trajectory, and hidden source packet. Three independent judge families reproduce the expert partial order at near-ceiling rates, showing that bounded, observable criteria support reliable evaluation. Across nine model families, basic deliverability is nearly saturated, while report identity and institutional completeness remain the primary bottlenecks. The largest cross-model gaps concern generation-trace control, information density, and data discipline rather than basic report framing. We then use benchmark-guided skill distillation to turn recurrent failures into reusable generation and self-review constraints. Across five model families, the evolved skill improves mean G1 by 33.85 points and mean G2 by 13.83 points over paired no-skill runs while preserving G0 for every pair. Code and benchmark artifacts are available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.04374 — 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 2026-10-31T11:02:13.500Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).