It is concluded that while LLMs hold genuine promise within AI trading systems, robust deployment requires careful task decomposition, rigorous backtesting protocols, and domain-aware fine-tuning strategies.
This thesis uses a cheap, off-the-shelf measure of Environmental, Social and Governance content in financial text by monitoring the internal activations of frozen, out-of-the-box LLMs and finds that these methods come close to fully fine-tuned models without any task-specific fine-tuning.
Hierarchical Reranker is proposed, a deployable, domain-optimized RAG pipeline that enhances both the accuracy and scalability of financial reasoning, paving the way for automated audit reporting and quantitative investment analysis.
This study analyzes annual reports of firms listed on Borsa Istanbul (BIST) for the period from 1990 to 2026, and demonstrates that data-driven initia’sation significantly improves topi’sc interpretability, reduces optimization iterations, decreases model uncertainty, and en’hances reproducibility compared with tr...
FinVision is presented, a multimodal large language model that unites vision-language models with domain-specific financial reasoning and reduces valuation error by 19 percent relative to the strongest baseline; a user study with 48 accounting and investment professionals reported a 51 percent reduction in task complet...
We present the IGT system for PolyFiQA Task 2 of the FinMMEval Lab at CLEF 2026, a multilingual financial question answering task over English SEC filings and multilingual news articles (English, Chinese, Japanese, Spanish, Greek) for four companies. Our central observation is that the 344 development questions divide...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
