{"slug": "cross-lingual-reusability-of-llm-pipelines-financial-extraction-multilingual-and", "title": "Cross-Lingual Reusability of LLM Pipelines: Financial Extraction, Multilingual Reasoning, and Semantic Screening", "summary": "A study posted to arXiv (2610.27043v1) found that English-built LLM pipelines can be reused across languages with qualifications: Gemini 3.5 Flash reached 95.2–97.6% cheque-extraction accuracy across prompt languages, and FinanceBench per-language means spanned 5.8 percentage points (77.1–82.9%) over 50 items from SEC 10-K filings in four languages. Higher reasoning effort produced only marginal gains on general-knowledge QA but up to 8 percentage points on financial content, while citation-set overlap with English averaged 77–79% Jaccard across the nine languages tested on Mintaka. The authors conclude that per-domain, per-language validation remains necessary because neither semantic similarity nor self-reported confidence reliably predicts cross-lingual accuracy.", "body_md": "arXiv:2610.27043v1 Announce Type: new \nAbstract: Financial institutions increasingly deploy large language models (LLMs) in multilingual markets, raising a practical question: can pipelines developed and validated in English be reused across languages, or must they be rebuilt per locale? We test cross-lingual reusability along three dimensions--accuracy, reasoning-effort transfer, and behavioural stability--through three complementary tasks. Task 1 (cheque extraction) and Task 2 (Mintaka QA with pinned evidence across nine languages and nine model-effort configurations) test whether accuracy and effort settings transfer; Task 3 (FinanceBench pilot, 50 items over SEC 10-K filings in four languages) validates whether these patterns generalise to financial content. Accuracy reusability is broadly confirmed: Gemini 3.5 Flash achieves 95.2-97.6% extraction accuracy across prompt languages, and FinanceBench per-language means span 5.8pp (77.1-82.9%), though the language-difficulty ranking reverses between domains (Hindi is worst on Mintaka, best on FinanceBench at 82.9%). Effort reusability is domain-dependent: higher reasoning effort yields marginal gains on general-knowledge QA but up to 8pp on financial content, and effort configurations that help in English help proportionally in other languages. Behavioural reusability holds: citation-set overlap with English averages 77-79% Jaccard, with no single language consistently worse. Together, these results support qualified reuse of English-built pipelines, but per-domain, per-language validation remains necessary--neither semantic similarity nor self-reported confidence reliably predicts cross-lingual accuracy.", "url": "https://wpnews.pro/news/cross-lingual-reusability-of-llm-pipelines-financial-extraction-multilingual-and", "canonical_source": "https://arxiv.org/abs/2610.27043", "published_at": "2026-10-21 04:00:00+00:00", "updated_at": "2026-10-21 04:18:16.964127+00:00", "lang": "en", "topics": ["large-language-models", "ai-research", "natural-language-processing", "machine-learning"], "entities": ["arXiv", "Gemini 3.5 Flash", "Mintaka", "FinanceBench", "SEC"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/cross-lingual-reusability-of-llm-pipelines-financial-extraction-multilingual-and", "markdown": "https://wpnews.pro/news/cross-lingual-reusability-of-llm-pipelines-financial-extraction-multilingual-and.md", "text": "https://wpnews.pro/news/cross-lingual-reusability-of-llm-pipelines-financial-extraction-multilingual-and.txt", "jsonld": "https://wpnews.pro/news/cross-lingual-reusability-of-llm-pipelines-financial-extraction-multilingual-and.jsonld"}}