IndicIFEval: A Benchmark for Verifiable Instruction-Following Evaluation in 14 Indic Languages
This addresses a critical evaluation gap for hundreds of millions of Indic language speakers, though it is incremental as it extends existing benchmarks to new languages.
The authors tackled the lack of instruction-following benchmarks for Indic languages by introducing IndicIFEval, a benchmark across 14 Indic languages with around 800 examples per language, finding that models struggle with lexical and cross-lingual tasks and lag behind English performance.
Instruction-following benchmarks remain predominantly English-centric, leaving a critical evaluation gap for the hundreds of millions of Indic language speakers. We introduce IndicIFEval, a benchmark evaluating constrained generation of LLMs across 14 Indic languages using automatically verifiable, rule-based instructions. It comprises around 800 human-verified examples per language spread across two complementary subsets: IndicIFEval-Ground, translated prompts from IFEval (Zhou et al., 2023) carefully localized for Indic contexts, and IndicIFEval-Ground, synthetically generated instructions grounded in native Indic content. We conduct a comprehensive evaluation of major open-weight and proprietary models spanning both reasoning and non-reasoning models. While models maintain strong adherence to formatting constraints, they struggle significantly with lexical and cross-lingual tasks -- and despite progress in high-resource languages, instruction-following across the broader Indic family lags significantly behind English. We release IndicIFEval and its evaluation scripts to support progress on multilingual constrained generation (http://github.com/ai4bharat/IndicIFEval).