{"slug": "causal-connections-leveraging-multilingual-fine-tuning-for-financial-qa-2026", "title": "Causal Connections: Leveraging Multilingual Fine-Tuning for Financial QA@FinCausal 2026", "summary": "Team HSA_CORAL submitted to the FinCausal 2026 shared task on extracting cause-effect relations from financial narratives via extractive question answering in English and Spanish. Their best system, GPT-4.1 Mini fine-tuned on combined English and Spanish training data, achieved a tied highest score on the English subtask and ranked third on Spanish. The results highlight the value of task-specific adaptation and multilingual fine-tuning for cross-lingual transfer in financial causality QA.", "body_md": "arXiv:2606.27446v1 Announce Type: new\nAbstract: 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 performance, while supervised fine-tuning provides the largest gains. Our best system, GPT-4.1 Mini fine-tuned on combined English and Spanish training data, achieves a tied highest score on the English subtask (score 4.8140) and ranks third on Spanish (score 4.7753) under the shared task's LLM-as-a-judge metric. Overall, the results highlight the value of task-specific adaptation and multilingual fine-tuning for cross-lingual transfer in financial causality QA.", "url": "https://wpnews.pro/news/causal-connections-leveraging-multilingual-fine-tuning-for-financial-qa-2026", "canonical_source": "https://arxiv.org/abs/2606.27446", "published_at": "2026-06-29 04:00:00+00:00", "updated_at": "2026-06-29 04:07:01.368604+00:00", "lang": "en", "topics": ["natural-language-processing", "large-language-models", "ai-research", "machine-learning"], "entities": ["HSA_CORAL", "FinCausal 2026", "BERT", "BART", "Llama 3.1", "GPT-4.1 Mini", "GPT"], "alternates": {"html": "https://wpnews.pro/news/causal-connections-leveraging-multilingual-fine-tuning-for-financial-qa-2026", "markdown": "https://wpnews.pro/news/causal-connections-leveraging-multilingual-fine-tuning-for-financial-qa-2026.md", "text": "https://wpnews.pro/news/causal-connections-leveraging-multilingual-fine-tuning-for-financial-qa-2026.txt", "jsonld": "https://wpnews.pro/news/causal-connections-leveraging-multilingual-fine-tuning-for-financial-qa-2026.jsonld"}}