# Causal Connections: Leveraging Multilingual Fine-Tuning for Financial QA@FinCausal 2026

Source: [Causal Connections: Leveraging Multilingual Fine-Tuning for Financial QA@FinCausal 2026](<https://www.sota2.com/research/paper/6a41fc11206542251d7ccae3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-30T05:00:05.200Z

Authors: Akash Kumar Gautam, Serhii Hamotskyi, Christian H\\"anig

Published: 2026-06-25T18:17:04.000Z

## 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 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Extractive Question Answering for Causal Relations on FinCausal English 2026 (test)](<https://www.sota2.com/research/sota/extractive-question-answering-for-causal-relations-on-fincausal-english-2026-test.md>): Extractive Question Answering for Causal Relations; FinCausal English 2026 (test); LLM Judge Score: 4.814.

- [Extractive Question Answering for Causal Relations on FinCausal Spanish 2026 (test)](<https://www.sota2.com/research/sota/extractive-question-answering-for-causal-relations-on-fincausal-spanish-2026-test.md>): Extractive Question Answering for Causal Relations; FinCausal Spanish 2026 (test); LLM Judge Score: 4.7753.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.27446>)

[PDF](<https://arxiv.org/pdf/2606.27446.pdf>)