QUENCH: Measuring the gap between Indic and Non-Indic Contextual General Reasoning in LLMs
This work addresses the need for better benchmarking of LLMs' world knowledge and deduction, particularly for domain-specific applications in geographical reasoning, though it is incremental as it builds on existing benchmarking efforts.
The authors tackled the problem of evaluating LLMs' contextual reasoning across geographical contexts by introducing QUENCH, a benchmark based on English quiz videos, and found that LLMs show a gap between Indic and non-Indic reasoning, with specific performance metrics reported across 7 models.
The rise of large language models (LLMs) has created a need for advanced benchmarking systems beyond traditional setups. To this end, we introduce QUENCH, a novel text-based English Quizzing Benchmark manually curated and transcribed from YouTube quiz videos. QUENCH possesses masked entities and rationales for the LLMs to predict via generation. At the intersection of geographical context and common sense reasoning, QUENCH helps assess world knowledge and deduction capabilities of LLMs via a zero-shot, open-domain quizzing setup. We perform an extensive evaluation on 7 LLMs and 4 metrics, investigating the influence of model size, prompting style, geographical context, and gold-labeled rationale generation. The benchmarking concludes with an error analysis to which the LLMs are prone.