# PARIKSHA: A Large-Scale Investigation of Human-LLM Evaluator Agreement on Multilingual and Multi-Cultural Data

arXiv: https://arxiv.org/abs/2406.15053 · HTML: https://mlsanity.com/paper/2406.15053/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 67 references that are in the map.
- First posted on arXiv 21 Jun 2024.

## Builds on (most cited first, 30 of 35)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization](https://mlsanity.com/paper/2003.11080/) (2020)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Large Language Models Are State-of-the-Art Evaluators of Translation Quality](https://mlsanity.com/paper/2302.14520/) (2023)
- [Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model](https://mlsanity.com/paper/2402.07827/) (2024)
- [MEGA: Multilingual Evaluation of Generative AI](https://mlsanity.com/paper/2303.12528/) (2023)
- [Proving Test Set Contamination in Black Box Language Models](https://mlsanity.com/paper/2310.17623/) (2023)
- [Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs](https://mlsanity.com/paper/2402.03927/) (2024)
- [XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation](https://mlsanity.com/paper/2004.01401/) (2020)
- [Rethinking Benchmark and Contamination for Language Models with Rephrased Samples](https://mlsanity.com/paper/2311.04850/) (2023)
- [Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning](https://mlsanity.com/paper/2402.06619/) (2024)
- [XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation](https://mlsanity.com/paper/2104.07412/) (2021)
- [IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages](https://mlsanity.com/paper/2305.16307/) (2023)
- [Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages](https://mlsanity.com/paper/2212.05409/) (2022)
- [Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?](https://mlsanity.com/paper/2309.07462/) (2023)
- [Human Feedback is not Gold Standard](https://mlsanity.com/paper/2309.16349/) (2023)
- [Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMs](https://mlsanity.com/paper/2310.07251/) (2023)
- [Elo Uncovered: Robustness and Best Practices in Language Model Evaluation](https://mlsanity.com/paper/2311.17295/) (2023)
- [IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languages](https://mlsanity.com/paper/2404.16816/) (2024)
- [IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages](https://mlsanity.com/paper/2203.05437/) (2022)
- [RTP-LX: Can LLMs Evaluate Toxicity in Multilingual Scenarios?](https://mlsanity.com/paper/2404.14397/) (2024)
- [Tamil-Llama: A New Tamil Language Model Based on Llama 2](https://mlsanity.com/paper/2311.05845/) (2023)

## Built on by (most cited first, 30 of 37)

- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [How Reliable is Multilingual LLM-as-a-Judge?](https://mlsanity.com/paper/2505.12201/) (2025)
- [BLEUBERI: BLEU is a surprisingly effective reward for instruction following](https://mlsanity.com/paper/2505.11080/) (2025)
- [Evaluating Tokenizer Performance of Large Language Models Across Official Indian Languages](https://mlsanity.com/paper/2411.12240/) (2024)
- [Llama-3-Nanda-10B-Chat: An Open Generative Large Language Model for Hindi](https://mlsanity.com/paper/2504.06011/) (2025)
- [FairI Tales: Evaluation of Fairness in Indian Contexts with a Focus on Bias and Stereotypes](https://mlsanity.com/paper/2506.23111/) (2025)
- [Faux Polyglot: A Study on Information Disparity in Multilingual Large Language Models](https://mlsanity.com/paper/2407.05502/) (2024)
- [One world, one opinion? The superstar effect in LLM responses](https://mlsanity.com/paper/2412.10281/) (2024)
- [A Multilingual, Culture-First Approach to Addressing Misgendering in LLM Applications](https://mlsanity.com/paper/2503.20302/) (2025)
- [Building Benchmarks from the Ground Up: Community-Centered Evaluation of LLMs in Healthcare Chatbot Settings](https://mlsanity.com/paper/2509.24506/) (2025)
- [IndicJR: A Judge-Free Benchmark of Jailbreak Robustness in South Asian Languages](https://mlsanity.com/paper/2602.16832/) (2026)
- [HEALTH-PARIKSHA: Assessing RAG Models for Health Chatbots in Real-World Multilingual Settings](https://mlsanity.com/paper/2410.13671/) (2024)
- [UPDESH: Synthesizing Grounded Instruction Tuning Data for 13 Indic Languages](https://mlsanity.com/paper/2509.21294/) (2025)
- [Synthetic Voice Data for Automatic Speech Recognition in African Languages](https://mlsanity.com/paper/2507.17578/) (2025)
- [ParamBench: A Graduate-Level Benchmark for Evaluating LLM Understanding on Indic Subjects](https://mlsanity.com/paper/2508.16185/) (2025)
- [BRoverbs -- Measuring how much LLMs understand Portuguese proverbs](https://mlsanity.com/paper/2509.08960/) (2025)
- [MENLO: From Preferences to Proficiency -- Evaluating and Modeling Native-like Quality Across 47 Languages](https://mlsanity.com/paper/2509.26601/) (2025)
- [IndicParam: Benchmark to evaluate LLMs on low-resource Indic Languages](https://mlsanity.com/paper/2512.00333/) (2025)
- [A Principle-based Framework for the Development and Evaluation of Large Language Models for Health and Wellness](https://mlsanity.com/paper/2512.08936/) (2025)
- [IndicSafe: A Benchmark for Evaluating Multilingual LLM Safety in South Asia](https://mlsanity.com/paper/2603.17915/) (2026)
- [The Geometry of LLM-as-Judge: Why Inter-LLM Consensus Is Not Human Alignment](https://mlsanity.com/paper/2606.03043/) (2026)
- [Revealing the impact of synthetic native samples and multi-tasking strategies in Hindi-English code-mixed humour and sarcasm detection](https://mlsanity.com/paper/2412.12761/) (2024)
- [ELR-1000: A Community-Generated Dataset for Endangered Indic Indigenous Languages](https://mlsanity.com/paper/2512.01077/) (2025)
- [XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity](https://mlsanity.com/paper/2605.05662/) (2026)
- [MEDAL: A Framework for Benchmarking LLMs as Multilingual Open-Domain Dialogue Evaluators](https://mlsanity.com/paper/2505.22777/) (2025)
- [BHRAM-IL: A Benchmark for Hallucination Recognition and Assessment in Multiple Indian Languages](https://mlsanity.com/paper/2512.01852/) (2025)
- [Auditing Stealth Sycophancy in Mental-Health Dialogue: Structured Clinical-State Diagnostics and Clean Matched Benchmarks](https://mlsanity.com/paper/2605.03472/) (2026)
- [Challenges and Recommendations for LLM-as-a-Judge in Multilingual Settings and for Low-Resource Languages](https://mlsanity.com/paper/2607.02235/) (2026)
- [Register Shifts Break LLM Safety: A Bengali Benchmark with Culturally Grounded Harms](https://mlsanity.com/paper/2608.22335/) (2026)
- [Opening LLM Judges: Recovering Preference Signals Beyond the Final Verdict](https://mlsanity.com/paper/2609.32407/) (2026)

## Abstract (arXiv)

Evaluation of multilingual Large Language Models (LLMs) is challenging due to a variety of factors -- the lack of benchmarks with sufficient linguistic diversity, contamination of popular benchmarks into LLM pre-training data and the lack of local, cultural nuances in translated benchmarks. In this work, we study human and LLM-based evaluation in a multilingual, multi-cultural setting. We evaluate 30 models across 10 Indic languages by conducting 90K human evaluations and 30K LLM-based evaluations and find that models such as GPT-4o and Llama-3 70B consistently perform best for most Indic languages. We build leaderboards for two evaluation settings - pairwise comparison and direct assessment and analyze the agreement between humans and LLMs. We find that humans and LLMs agree fairly well in the pairwise setting but the agreement drops for direct assessment evaluation especially for languages such as Bengali and Odia. We also check for various biases in human and LLM-based evaluation and find evidence of self-bias in the GPT-based evaluator. Our work presents a significant step towards scaling up multilingual evaluation of LLMs.