arXiv:2606.27446v1 Announce Type: new Abstract: This paper describes team HSA_CORAL's submission to the FinCausal 2026 shared task on extracting cause-effect relations from financial narratives via extractive question answering in English and Spanish. We compare three modeling families: (i) encoder-only token tagging with multilingual BERT, (ii) encoder-decoder generation with multilingual BART, and (iii) decoder-only LLMs (Llama 3.1 and GPT variants) using prompt refinement, few-shot demonstrations, and supervised fine-tuning. Across settings, prompting and few-shot examples yield competitive
The proliferation of Large Language Models (LLMs) and the increasing complexity of financial data necessitate advanced NLP techniques for efficient information extraction.
This development highlights the growing application of advanced AI in financial analysis, potentially streamlining complex tasks and improving decision-making in the financial sector.
The ability to accurately extract causal relationships from financial narratives in multiple languages will enhance the automation of financial intelligence gathering and risk assessment.
- · Financial analysts
- · Quantitative trading firms
- · Financial AI/ML developers
- · Multinational financial institutions
- · Manual financial data processors
- · Legacy financial NLP solutions
Improved efficiency and accuracy in financial narrative analysis, especially for cause-effect relationships.
Increased adoption of AI agents for financial insights, potentially leading to more automated investment strategies.
Enhanced AI-driven risk models that can better predict market shifts based on causal connections identified in financial news.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.CL