Metraipolis › archive › dc_c04ea0b3b9cd

FinCutBench: A Continually Updated Benchmark for Measuring the Temporal Boundaries of LLM Financial Knowledge — arXiv:2611.11588

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.11588
License (as archived)
CC0-1.0
Archived
2026-11-10T18:41:25.488Z
SHA-256 of the archived text
930be324ad94e06519feac4969def1dd47ef39622a6132a8cbd78a01a612531a
Stable URL of this page
https://metraipolis.com/documento/dc_c04ea0b3b9cd

How to cite

FinCutBench: A Continually Updated Benchmark for Measuring the Temporal Boundaries of LLM Financial Knowledge — arXiv:2611.11588 — arXiv (en), https://arxiv.org/abs/2611.11588 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c04ea0b3b9cd (Metraipolis archive dc_c04ea0b3b9cd, sha256 930be324ad94e06519feac4969def1dd47ef39622a6132a8cbd78a01a612531a)
BibTeX
@misc{dcc04ea0b3b9cd,
  title = {FinCutBench: A Continually Updated Benchmark for Measuring the Temporal Boundaries of LLM Financial Knowledge — arXiv:2611.11588},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.11588},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c04ea0b3b9cd; sha256 930be324ad94e06519feac4969def1dd47ef39622a6132a8cbd78a01a612531a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.11588. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In financial backtesting and other point-in-time tasks, external inputs can be restricted by date, but model parameters may retain financial facts disclosed later, introducing parametric look-ahead bias. We introduce FinCutBench, a continually updated monthly financial knowledge benchmark for measuring how far a fixed model's financial knowledge extends over calendar time. The current dataset contains 9,000 Chinese and English four-option multiple-choice questions from January 2023 to September 2026, covering Chinese and U.S. markets and four categories of financial information. We construct monthly knowledge profiles using the approximate months in which the tested facts became public. After a profile passes the decline test and knot checks, we define the FinCut Boundary as the first month when the fitted profile reaches its lower level, and report the stability of the estimated date under resampling. Boundary dates and localization precision vary across models. Using the independently measured Transition Start and Boundary as fixed references for downstream sample grouping, we find clear relative declines after the Boundary in U.S. asset ranking and earnings recall for some models, while Chinese-market ranking estimates vary across models and all eight disclosure-period-paired forecast-error comparisons have unadjusted $p$ values above 0.10. The FinCut Boundary thus provides an empirical reference for the temporal scope of parametric knowledge in point-in-time financial evaluation, supporting evaluation-window selection and result interpretation.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.11588 — 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 2026-11-10T18:37:37.515Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).