{"paper_id":"2404.10555","title":"Construction of Domain-specified Japanese Large Language Model for Finance through Continual Pre-training","authors":["Masanori Hirano","Kentaro Imajo"],"paper_date":"2024-04-16","paper_type":"dataset-benchmark","paper_url":"https://arxiv.org/pdf/2404.10555v1","page_url":"https://thequant.space/flowcharts/construction-of-domain-specified-japanese-large-language-mod/","scores":{"empirical_rigor":8.5,"math_complexity":1.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes constructing a Japanese financial‑specific large language model by continual pre‑training on domain‑focused data.","quote":"Hence, this study aims to construct a Japanese financial-specific LLM through continual pre-training.","summary":"Large language models (LLMs) are now widely used in various fields, including finance. However, Japanese financial-specific LLMs have not been proposed yet. Hence, this study aims to construct a Japanese financial-specific LLM through continual pre-training. Before tuning, we constructed Japanese…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Continual pre‑training is effective for domain‑specific tuning.","type":"model","stated":"explicit","quote":"Therefore, we employed the continual pre-training method for domain-specific tuning in this study."},{"assumption":"The base model is state‑of‑the‑art for Japanese financial benchmarks.","type":"model","stated":"explicit","quote":"we need to employ the state-of-the-art model as a base model."},{"assumption":"The constructed datasets are legally usable for commercial purposes in Japan as of April 2024.","type":"data","stated":"explicit","quote":"The datasets are currently clear to use for commercial purposes under Japanese law as of April 2024."},{"assumption":"Benchmark scores reflect model performance on Japanese financial tasks.","type":"statistical","stated":"implied","quote":"The tuned model achieved better performance than the original model in all tasks."}]},"datasets":{"status":"available","items":[{"name":"Japanese financial‑focused datasets","provider":"crawled articles from the Internet","kind":"text-news","access":"public","period":null,"universe":null,"quote":"The crawled articles mainly include the following types of documents: • Speeches, Press Conferences, and Talks of Officers of the Bank of Japan • Minutes of the Monetary Policy Meetings of the Bank of Japan • Reports, glossaries, and company profiles from multiple financial institutions • Financial-related documents ex"}],"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":"The tuned model’s overall benchmark score is 0.4716, which is +0.0381 higher than the original model’s score of 0.4335.","kind":"performance","quote":"The overall score of the tuned model is 0.4716, which is +0.0381 higher than the original model’s score (0.4335)."},{"finding":"The tuned model outperforms the original model on every individual benchmark task.","kind":"performance","quote":"The tuned model achieved better performance than the original model in all tasks."},{"finding":"During continual pre‑training, the loss curve showed no spikes and saturated as the learning rate decayed linearly to zero.","kind":"statistical","quote":"In our tuning, no loss spikes were observed. The loss curve was also saturated as the learning rate decayed linearly to 0."},{"finding":"Outputs from the tuned model tend to be better than those from the original model in terms of quality and length of answers.","kind":"other","quote":"According to those examples, the tuned model’s outputs tend to be better than the original model’s outputs in terms of the quality and length of the answers."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":15,"citations":{"cited_by_in_corpus":1,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"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/pfnet/nekomata-14b-pfn-qfin","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":"2026-11-14T18:10:59Z"},"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/"}