# Learn and Unlearn: Addressing Misinformation in Multilingual LLMs

arXiv: https://arxiv.org/abs/2406.13748 · HTML: https://mlsanity.com/paper/2406.13748/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 22 of its 32 references that are in the map.
- First posted on arXiv 19 Jun 2024.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 22 of 22)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://mlsanity.com/paper/2004.09813/) (2020)
- [Memory-Based Model Editing at Scale](https://mlsanity.com/paper/2206.06520/) (2022)
- [Who's Harry Potter? Approximate Unlearning in LLMs](https://mlsanity.com/paper/2310.02238/) (2023)
- [Editing Large Language Models: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2305.13172/) (2023)
- [NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark](https://mlsanity.com/paper/2310.18018/) (2023)
- [Few-shot Learning with Multilingual Language Models](https://mlsanity.com/paper/2112.10668/) (2021)
- [In-Context Unlearning: Language Models as Few Shot Unlearners](https://mlsanity.com/paper/2310.07579/) (2023)
- [Knowledge Editing for Large Language Models: A Survey](https://mlsanity.com/paper/2310.16218/) (2023)
- [Cross-Lingual Ability of Multilingual BERT: An Empirical Study](https://mlsanity.com/paper/1912.07840/) (2019)
- [Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting](https://mlsanity.com/paper/2305.07004/) (2023)
- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2201.05273/) (2022)
- [The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts](https://mlsanity.com/paper/2401.13136/) (2024)
- [Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing](https://mlsanity.com/paper/1902.09492/) (2019)
- [Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages](https://mlsanity.com/paper/2402.12204/) (2024)
- [Improving Multilingual Translation by Representation and Gradient Regularization](https://mlsanity.com/paper/2109.04778/) (2021)
- [Cross-Lingual Unlearning of Selective Knowledge in Multilingual Language Models](https://mlsanity.com/paper/2406.12354/) (2024)

## Built on by (most cited first, 12 of 12)

- [Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment](https://mlsanity.com/paper/2502.11244/) (2025)
- [Rethinking Cross-lingual Alignment: Balancing Transfer and Cultural Erasure in Multilingual LLMs](https://mlsanity.com/paper/2510.26024/) (2025)
- [A Survey on Unlearning in Large Language Models](https://mlsanity.com/paper/2510.25117/) (2025)
- [The Facade of Truth: Uncovering and Mitigating LLM Susceptibility to Deceptive Evidence](https://mlsanity.com/paper/2601.05478/) (2026)
- [Evaluating Cross-Lingual Unlearning in Multilingual Language Models](https://mlsanity.com/paper/2601.06675/) (2026)
- [Layer-Targeted Multilingual Knowledge Erasure in Large Language Models](https://mlsanity.com/paper/2602.22562/) (2026)
- [Multilingual Unlearning in LLMs: Transfer, Dynamics, and Reversibility](https://mlsanity.com/paper/2606.03291/) (2026)
- [Beyond Cross-Lingual Transfer: Benchmarking Propagation Boundaries in Multilingual LLM Unlearning](https://mlsanity.com/paper/2609.05976/) (2026)
- [Unlearning in LLMs: Methods, Evaluation, and Open Challenges](https://mlsanity.com/paper/2601.13264/) (2026)
- [QR-Erase: Efficient Subspace-Based Machine Unlearning with Layer Localization](https://mlsanity.com/paper/2608.01422/) (2026)
- [μ2-Bench: A Multilingual Machine Unlearning Benchmark](https://mlsanity.com/paper/2609.20945/) (2026)
- [Linguistic Loopholes in LLM Unlearning: From a 174-Language Benchmark to Coverage-Aware Unlearning](https://mlsanity.com/paper/2609.40286/) (2026)

## Abstract (arXiv)

This paper investigates the propagation of harmful information in multilingual large language models (LLMs) and evaluates the efficacy of various unlearning methods. We demonstrate that fake information, regardless of the language it is in, once introduced into these models through training data, can spread across different languages, compromising the integrity and reliability of the generated content. Our findings reveal that standard unlearning techniques, which typically focus on English data, are insufficient in mitigating the spread of harmful content in multilingual contexts and could inadvertently reinforce harmful content across languages. We show that only by addressing harmful responses in both English and the original language of the harmful data can we effectively eliminate generations for all languages. This underscores the critical need for comprehensive unlearning strategies that consider the multilingual nature of modern LLMs to enhance their safety and reliability across diverse linguistic landscapes.