{"paper_id":"2511.08621","title":"The LLM Pro Finance Suite: Multilingual Large Language Models for Financial Applications","authors":["Gaëtan Caillaut","Raheel Qader","Jingshu Liu","Mariam Nakhlé","Arezki Sadoune","Massinissa Ahmim","Jean-Gabriel Barthelemy"],"paper_date":"2025-11-07","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2511.08621v1","page_url":"https://thequant.space/flowcharts/the-llm-pro-finance-suite-multilingual-large-language-model/","scores":{"empirical_rigor":8,"math_complexity":1.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper introduces the LLM Pro Finance Suite, a collection of five instruction‑tuned large language models ranging from 8B to 70B parameters for financial applications.","quote":"To address this gap, we introduce the LLM Pro Finance Suite, a collection of five instruction‑tuned LLMs (ranging from 8B to 70B parameters) specifically designed for financial applications.","summary":"The financial industry’s growing demand for advanced natural language processing (NLP) capabilities has highlighted the limitations of generalist large language models (LLMs) in handling domain-specific financial tasks. To address this gap, we introduce the LLM Pro Finance Suite, a collection of…","strategy":null},"assumptions":{"status":"none_found","items":[]},"datasets":{"status":"available","items":[{"name":"curated financial corpus","provider":null,"kind":"text-news","access":"unknown","period":null,"universe":null,"quote":"fine‑tuning them on a curated, high‑quality financial corpus comprising over 50 % finance‑related data in English, French, and German."},{"name":"SFT dataset","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"The SFT dataset combines open‑source resources from Hugging Face Hub with synthetic data generated from text documents."},{"name":"in‑house financial translation dataset","provider":null,"kind":"text-news","access":"unknown","period":null,"universe":null,"quote":"We evaluated the translation capabilities of LLM Pro Finance models using an in‑house translation dataset covering 8 languages and 22 directions."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"none"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"LLM Pro Finance models achieve consistent improvement over state‑of‑the‑art baselines on finance‑oriented tasks and financial translation, while maintaining general‑domain performance.","kind":"performance","quote":"We evaluate the LLM Pro Finance Suite on a comprehensive financial benchmark suite, demonstrating consistent improvement over state‑of‑the‑art baselines in finance‑oriented tasks and financial translation."},{"finding":"On non‑financial benchmarks the Pro Finance models are generally on par with their baseline models, indicating no degradation of general‑domain knowledge.","kind":"performance","quote":"The LLM Pro Finance models are generally on par with their baseline models, indicating that general domain knowledge and natural language understanding capabilities are not degraded through the adaptation to the financial domain."},{"finding":"Pro Finance models outperform baselines in understanding financial acronyms, with accuracy gains ranging from ~10 % to >60 % across languages.","kind":"performance","quote":"The Pro Finance models consistently out‑perform their baseline"},{"finding":"Financial translation performance improves significantly, with an average BLEU improvement of around 15 % across all directions for the three largest models.","kind":"performance","quote":"The performance of all models improved significantly, with an average improvement around 15 % overall. We also show the absolute BLEU"},{"finding":"Training on the same dataset increased toxicity for two models while decreasing it by more than 50 % for two others, showing that data filtering alone does not guarantee safety.","kind":"negative","quote":"we were surprised to observe that training on the same dataset resulted in a substantial increase in toxicity for two models, while leading to more than a 50 % decrease for two others."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":31,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://huggingface.co/collections/OVHaiLLM/llm-open-finance","note":null},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:22:12Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}