Causal Connections: Leveraging Multilingual Fine-Tuning for Financial QA@FinCausal 2026
For participants in financial NLP shared tasks, this paper shows that multilingual fine-tuning of LLMs can achieve competitive cross-lingual performance, though the gains are incremental over existing methods.
The team HSA_CORAL achieved the highest score on English (4.8140) and third on Spanish (4.7753) in the FinCausal 2026 shared task by fine-tuning GPT-4.1 Mini on multilingual data, demonstrating the effectiveness of task-specific adaptation for cross-lingual financial causality QA.
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.