首页 > AI前沿 > V\={a}kQA: A Benchmark and Evaluation Study for Telugu Spoken Factoid Question Answering

V\={a}kQA: A Benchmark and Evaluation Study for Telugu Spoken Factoid Question Answering

arXiv自然语言 2026-09-17 16:29 3 阅读 查看原文

Introduction and Motivation

Question answering has advanced rapidly with large language models, but predominantly for high-resource languages, in both text and spoken settings. Spoken question answering (SQA) benchmark for Telugu remains unexplored, and the reliability of automatic evaluation in this setting remains unquantified.

Benchmark Dataset: VākQA

We introduce VākQA, a Telugu SQA benchmark of 2,001 factoid question-answer pairs across six domains, with 2.53 hours of speech audio, bilingual transcriptions, and human-verified reference answers.

Evaluation Methodology

We first validate evaluation methods against human judgements:

  • Gemini-as-a-judge best approximates human ratings but is non-uniformly strict.
  • Open-weight judges systematically penalize correct Telugu answers that differ in surface form from the reference.

Experimental Findings

Using this validated setup, we benchmark proprietary and open-weight models across input modality, language, and domain. We observe that:

  • Telugu phrasing retains cultural specificity that is lost in translation.
  • Speech input introduces phonetic confusions that alter question meaning.
  • Cascaded ASR-MT errors compound progressively.

Release

VākQA is publicly released.