Simorgh at SemEval-2026 task 7: Region-Aware Hybrid Retrieval for Low-Resource Cultural Reasoning in Multilingual Question Answering
For multilingual QA systems, this work tackles cultural reasoning in low-resource languages, though improvements are incremental and the data imbalance problem persists.
The paper addresses culturally grounded QA in low-resource languages using the BLEnD benchmark. Their region-aware hybrid retrieval (BM25 + dense similarity with regional weighting) improves cross-lingual stability over pure parametric inference, but performance gaps remain due to training data imbalance.
Although Large Language Models (LLMs) demonstrate excellent capabilities and performance for general reasoning tasks within the general public domain, they may face challenges with culturally grounded knowledge within languages with limited digital and textual data. In this paper, we investigate culturally grounded multiple-choice question answering with the BLEnD benchmark, which consists of a multilingual corpus of 30 languages and covers various socio-cultural domains, such as cuisine, sports, family, etc. We propose a region-aware hybrid retrieval approach that combines BM25 lexical matching and dense semantic similarity with regional weighting heuristics to improve the relevance of the answer. The retrieved documents are used to construct a structured prompt for the Qwen3-14B quantized model with logit-based deterministic answer selection. The experimental results show improvements to cross-lingual stability with the hybrid retrieval approach over pure parametric inference for culturally grounded question answering. However, there are still notable performance gaps between languages with more and less training data. This shows that the limitations of the retrieval augmentation approach are not entirely overcome by the training data imbalance problem.