SpokenNativQA: Multilingual Everyday Spoken Queries for LLMs
This addresses the problem of assessing LLM performance in real-world conversational settings for researchers and developers, but it is incremental as it focuses on dataset creation and benchmarking.
The authors tackled the lack of benchmarks for evaluating LLMs with multilingual spoken queries by introducing SpokenNativQA, a dataset of approximately 33,000 naturally spoken questions and answers in multiple languages, and benchmarked ASR systems and LLMs on it.
Large Language Models (LLMs) have demonstrated remarkable performance across various disciplines and tasks. However, benchmarking their capabilities with multilingual spoken queries remains largely unexplored. In this study, we introduce SpokenNativQA, the first multilingual and culturally aligned spoken question-answering (SQA) dataset designed to evaluate LLMs in real-world conversational settings. The dataset comprises approximately 33,000 naturally spoken questions and answers in multiple languages, including low-resource and dialect-rich languages, providing a robust benchmark for assessing LLM performance in speech-based interactions. SpokenNativQA addresses the limitations of text-based QA datasets by incorporating speech variability, accents, and linguistic diversity. We benchmark different ASR systems and LLMs for SQA and present our findings. We released the data at (https://huggingface.co/datasets/QCRI/SpokenNativQA) and the experimental scripts at (https://llmebench.qcri.org/) for the research community.