# How Much Do LLMs Hallucinate across Languages? On Realistic Multilingual Estimation of LLM Hallucination

arXiv: https://arxiv.org/abs/2502.12769 · HTML: https://mlsanity.com/paper/2502.12769/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 52 references that are in the map.
- First posted on arXiv 18 Feb 2025.

## Builds on (most cited first, 30 of 34)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders](https://mlsanity.com/paper/2404.05961/) (2024)
- [FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation](https://mlsanity.com/paper/2310.03214/) (2023)
- [Generate rather than Retrieve: Large Language Models are Strong Context Generators](https://mlsanity.com/paper/2209.10063/) (2022)
- [RealTime QA: What's the Answer Right Now?](https://mlsanity.com/paper/2207.13332/) (2022)
- [Fine-grained Hallucination Detection and Editing for Language Models](https://mlsanity.com/paper/2401.06855/) (2024)
- [A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation](https://mlsanity.com/paper/2104.08704/) (2021)
- [Hallucinations in Large Multilingual Translation Models](https://mlsanity.com/paper/2303.16104/) (2023)
- [Aya 23: Open Weight Releases to Further Multilingual Progress](https://mlsanity.com/paper/2405.15032/) (2024)
- [A Critical Evaluation of Evaluations for Long-form Question Answering](https://mlsanity.com/paper/2305.18201/) (2023)
- [EuroLLM: Multilingual Language Models for Europe](https://mlsanity.com/paper/2409.16235/) (2024)
- [When Search Engine Services meet Large Language Models: Visions and Challenges](https://mlsanity.com/paper/2407.00128/) (2024)
- [Detecting and Mitigating Hallucinations in Multilingual Summarisation](https://mlsanity.com/paper/2305.13632/) (2023)
- [mFACE: Multilingual Summarization with Factual Consistency Evaluation](https://mlsanity.com/paper/2212.10622/) (2022)
- [SEAHORSE: A Multilingual, Multifaceted Dataset for Summarization Evaluation](https://mlsanity.com/paper/2305.13194/) (2023)
- [A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection](https://mlsanity.com/paper/2310.06498/) (2023)
- [Revisiting Machine Translation for Cross-lingual Classification](https://mlsanity.com/paper/2305.14240/) (2023)
- [HalOmi: A Manually Annotated Benchmark for Multilingual Hallucination and Omission Detection in Machine Translation](https://mlsanity.com/paper/2305.11746/) (2023)
- [Looking Right is Sometimes Right: Investigating the Capabilities of Decoder-only LLMs for Sequence Labeling](https://mlsanity.com/paper/2401.14556/) (2024)
- [Fast and Accurate Factual Inconsistency Detection Over Long Documents](https://mlsanity.com/paper/2310.13189/) (2023)
- [Multi-Stage Prompting for Knowledgeable Dialogue Generation](https://mlsanity.com/paper/2203.08745/) (2022)
- [Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore](https://mlsanity.com/paper/2402.18045/) (2024)

## Built on by (most cited first, 5 of 5)

- [CrossHallu: Do Hallucination Signals Generalize Across Languages and Domains in Large Language Model's Internals?](https://mlsanity.com/paper/2607.04029/) (2026)
- [BenHalluEval: A Multi-Task Hallucination Evaluation Framework for Large Language Models on Bengali](https://mlsanity.com/paper/2605.31483/) (2026)
- [Lost in Speech: Trilingual Spoken Hallucination Detection Across Audio and Transcripts](https://mlsanity.com/paper/2608.24707/) (2026)
- [LTLGuard: Formalizing LTL Specifications with Compact Language Models and Lightweight Symbolic Reasoning](https://mlsanity.com/paper/2603.05728/) (2026)
- [SWORD: Wikidata-based Distortions Reveal Hidden Cross-Lingual Inconsistencies in LLM Factual Error Rejection](https://mlsanity.com/paper/2609.09349/) (2026)

## Abstract (arXiv)

In the age of misinformation, hallucination - the tendency of Large Language Models (LLMs) to generate non-factual or unfaithful responses - represents the main risk for their global utility. Despite LLMs becoming increasingly multilingual, the vast majority of research on detecting and quantifying LLM hallucination are (a) English-centric and (b) focus on machine translation (MT) and summarization, tasks that are less common in realistic settings than open information seeking. In contrast, we aim to quantify the extent of LLM hallucination across languages in knowledge-intensive long-form question answering (LFQA). To this end, we train a multilingual hallucination detection model and conduct a large-scale study across 30 languages and 6 open-source LLM families. We start from an English hallucination detection dataset and rely on MT to translate-train a detection model. We also manually annotate gold data for five high-resource languages; we then demonstrate, for these languages, that the estimates of hallucination rates are similar between silver (LLM-generated) and gold test sets, validating the use of silver data for estimating hallucination rates for other languages. For the final rates estimation, we build open-domain QA dataset for 30 languages with LLM-generated prompts and Wikipedia articles as references. Our analysis shows that LLMs, in absolute terms, hallucinate more tokens in high-resource languages due to longer responses, but that the actual hallucination rates (i.e., normalized for length) seems uncorrelated with the sizes of languages' digital footprints. We also find that smaller LLMs hallucinate more, and significantly, LLMs with broader language support display higher hallucination rates.