BHRAM-IL: A Benchmark for Hallucination Recognition and Assessment in Multiple Indian Languages

TL;DR

BHRAM-IL is a comprehensive benchmark designed to evaluate hallucination detection and assessment in multiple Indian languages, addressing a significant gap in multilingual NLP research.

Contribution

The paper introduces BHRAM-IL, a new benchmark with extensive data and evaluation metrics for hallucination recognition in Indian languages, including Hindi, Gujarati, Marathi, and Odia.

Findings

Multilingual LLMs show low hallucination detection scores on BHRAM-IL.

Cross-lingual analysis reveals language-specific hallucination patterns.

The benchmark provides a standardized way to evaluate and improve multilingual hallucination mitigation.

Abstract

Large language models (LLMs) are increasingly deployed in multilingual applications but often generate plausible yet incorrect or misleading outputs, known as hallucinations. While hallucination detection has been studied extensively in English, under-resourced Indian languages remain largely unexplored. We present BHRAM-IL, a benchmark for hallucination recognition and assessment in multiple Indian languages, covering Hindi, Gujarati, Marathi, Odia, along with English. The benchmark comprises 36,047 curated questions across nine categories spanning factual, numerical, reasoning, and linguistic tasks. We evaluate 14 state-of-the-art multilingual LLMs on a benchmark subset of 10,265 questions, analyzing cross-lingual and factual hallucinations across languages, models, scales, categories, and domains using category-specific metrics normalized to (0,1) range. Aggregation over all categories and models yields a primary score of 0.23 and a language-corrected fuzzy score of 0.385, demonstrating the usefulness of BHRAM-IL for hallucination-focused evaluation. The dataset, and the code for generation and evaluation are available on GitHub (https://github.com/sambhashana/BHRAM-IL/) and HuggingFace (https://huggingface.co/datasets/sambhashana/BHRAM-IL/) to support future research in multilingual hallucination detection and mitigation.