# Do LLM hallucination detectors suffer from low-resource effect?

arXiv: https://arxiv.org/abs/2601.16766 · HTML: https://mlsanity.com/paper/2601.16766/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 36 references that are in the map.
- First posted on arXiv 23 Jan 2026.

## Builds on (most cited first, 21 of 21)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [A Survey of Hallucination in Large Foundation Models](https://mlsanity.com/paper/2309.05922/) (2023)
- [The Impact of AI on Developer Productivity: Evidence from GitHub Copilot](https://mlsanity.com/paper/2302.06590/) (2023)
- [On Hallucination and Predictive Uncertainty in Conditional Language Generation](https://mlsanity.com/paper/2103.15025/) (2021)
- [Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models](https://mlsanity.com/paper/2402.14207/) (2024)
- [Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering](https://mlsanity.com/paper/2307.16877/) (2023)
- [Why Is My Classifier Discriminatory?](https://mlsanity.com/paper/1805.12002/) (2018)
- [X-FACTR: Multilingual Factual Knowledge Retrieval from Pretrained Language Models](https://mlsanity.com/paper/2010.06189/) (2020)
- [Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models](https://mlsanity.com/paper/2411.14257/) (2024)
- [Survey of Low-Resource Machine Translation](https://mlsanity.com/paper/2109.00486/) (2021)
- [On Early Detection of Hallucinations in Factual Question Answering](https://mlsanity.com/paper/2312.14183/) (2023)
- [Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models](https://mlsanity.com/paper/2504.04264/) (2025)
- [SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared Task on Hallucinations and Related Observable Overgeneration Mistakes](https://mlsanity.com/paper/2504.11975/) (2025)
- [Hierarchical Autoregressive Transformers: Combining Byte- and Word-Level Processing for Robust, Adaptable Language Models](https://mlsanity.com/paper/2501.10322/) (2025)
- [Geographical Erasure in Language Generation](https://mlsanity.com/paper/2310.14777/) (2023)
- [HalluVerse25: Fine-grained Multilingual Benchmark Dataset for LLM Hallucinations](https://mlsanity.com/paper/2503.07833/) (2025)
- [MILDSum: A Novel Benchmark Dataset for Multilingual Summarization of Indian Legal Case Judgments](https://mlsanity.com/paper/2310.18600/) (2023)
- [MILPaC: A Novel Benchmark for Evaluating Translation of Legal Text to Indian Languages](https://mlsanity.com/paper/2310.09765/) (2023)

## Built on by (most cited first, 4 of 4)

- [Can Humans Dream of Electric Sheep? Human-Written Samples for Fine-Grained Vision-and-Language Hallucination Benchmarking](https://mlsanity.com/paper/2608.01021/) (2026)
- [Peeking Inside LLMs: Leveraging Internal Artifacts of LLMs for Enhancing Reliability in Legal Classification](https://mlsanity.com/paper/2606.20929/) (2026)
- [Hard Negatives Reveal What Easy Negatives Hide: Cross-Lingual Harmfulness Representations Degrade with Resource Tier Under Hard Negatives](https://mlsanity.com/paper/2609.27758/) (2026)
- [Cross-lingual Calibration of Pre-Generation Success Probes for Multilingual LLM Routing](https://mlsanity.com/paper/2610.06216/) (2026)

## Abstract (arXiv)

LLMs, while outperforming humans in a wide range of tasks, can still fail in unanticipated ways. We focus on two pervasive failure modes: (i) hallucinations, where models produce incorrect information about the world, and (ii) the low-resource effect, where the models show impressive performance in high-resource languages like English but the performance degrades significantly in low-resource languages like Bengali. We study the intersection of these issues and ask: do hallucination detectors suffer from the low-resource effect? We conduct experiments on five tasks across three domains (factual recall, STEM, and Humanities). Experiments with four LLMs and three hallucination detectors reveal a curious finding: As expected, the task accuracies in low-resource languages experience large drops (compared to English). However, the drop in detectors' accuracy is often several times smaller than the drop in task accuracy. Our findings suggest that even in low-resource languages, the internal mechanisms of LLMs might encode signals about their uncertainty. Further, the detectors are robust within language (even for non-English) and in multilingual setups, but not in cross-lingual settings without in-language supervision.