arXiv cs.CL· Fazle Mohammed Tasfiq, Sabab Attin, Sheikh Md. Tahmid Hossain, Raiat Reza, Tanzim Ahmmed, Nafis Chowdhury, Anika Ahmed, Moinul Haque, Farig Yousuf Sadeque·· 3 天前AI 评分22
南亚多语言场景下 RAG 模型问答性能分析
Analyzing performance of Retrieval Augmented Generation models for Question Answering Tasks
AI 导读
一项研究分析了 RAG 模型在南亚多语言问答任务中的表现，探讨检索增强生成相比无上下文与有上下文回答能否提升正确率，以及 RAG 对文化类与非文化类问题的增益差异。研究还考察了 RAG 对热门与冷门文化问题的不同影响，旨在提炼高性能因素以指导优化混合 RAG 系统的设计。
正文 · 原文
Abstract:Retrieval-Augmented Generation (RAG) models have become almost a cornerstone of open-domain question answering tasks; in which the quality of answers generated in the process, greatly relies on the effectiveness of retrieval mechanisms. In the realm of LLM, the last two years have seen tremendous progress in RAG architectures, with many models reporting to have improved performance through various design innovations. The cultural question and answering systems of South Asia, in particular, present a specific challenge since the region is home to the vast number of languages and traditions, which are closely interrelated. Along with these deeply intertwined historical narratives increase the need for culturally grounded and context-aware interpretation. Despite major architectural advances in LLMs, claiming significant improvements, challenges remain when answering these region specific questions in native languages. In this study, we aim to extract high-performing factors to guide the development of optimized hybrid RAG systems. We further explore whether the integration of RAG changes performance differently for culturally grounded and non-cultural questions in a South Asian multilingual setup, and whether RAG produces a higher overall percentage of correct answers than contexted answering. We also examine how LLM performance changes when RAG methods are integrated into the question-answering pipeline in comparison with non-contexted and contexted answering and, evaluate whether the introduction of RAG benefits popular or non-popular culturally grounded questions more. Not only does our work evaluate the current methods but also carves a path for future designs of more accurate and efficient question-answering pipelines.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.20419 [cs.CL] |
| (or arXiv:2610.20419v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20419 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Raiat Reza [view email]
[v1]
Wed, 14 Oct 2026 16:14:55 UTC (2,056 KB)
来源：arXiv cs.CL · arxiv.org