LeedsMEng26: Qwen + Gemini for FinCausal 2026 Causality Detection in Financial Narrative Texts

Abstract

This paper presents the LeedsMEng26 system for the FinCausal 2026 shared task on financial causality detection in narrative texts. The task is formulated as extractive question answering over English and Spanish financial reports, where systems must return a verbatim span from the context that answers an abstractive question about a cause or an effect. We propose a two-stage pipeline consisting of candidate span generation followed by span verification and boundary refinement under a strict extractiveness constraint. We evaluate both an extractive RoBERTa-based baseline and instruction-tuned large language models. Results show that Qwen-2.5-1.5B-Instruct is a stronger candidate generator than the RoBERTa baseline, and that a second-stage verifier further improves answer boundary accuracy and overall adequacy. Our best configuration, Qwen-2.5-1.5B-Instruct with Gemini-2.5-flash refinement, achieved an adequacy score of 4.7000 for English and 4.6143 for Spanish. These findings suggest that a modular generation-and-verification pipeline is effective for extractive financial causality detection.

Resources

Details