Addressing Hallucination in Causal Q&A: The Efficacy of Fine-tuning over Prompting in LLMs

This paper presents our approach and findings for participating in the FinCausal 2025 competition (Moreno-Sandoval et al., 2025), which addresses causal question answering derived from financial documents, specifically English and Spanish annual reports. We investigate the effectiveness of generative models, such as Llama, in contrast to common extractive methods like BERT-based token classification. While prompt optimization and few-shot learning offer some improvements, they were insufficient for consistently outperforming extractive methods in FinCausal, suffering from hallucinations. In contrast, fine-tuning generative models was shown to be essential for minimizing hallucinations and achieving superior performance. Using our fine-tuned multilingual model for both tasks, we outperform our extractive and monolingual approaches, achieving top results for Spanish and second-best for English in the competition. Our findings indicate that fine-tuned large language models are well-suited for causal Q&A from complex financial narratives, offering robust multilingual capabilities and effectively mitigating hallucinations.