mlsanityData to 7 Oct 2026

Do Methods to Jailbreak and Defend LLMs Generalize Across Languages?

arXiv 2511.00689 ↗First posted 1 Nov 2025cs.CLcited by 4

On the map: LLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks

also in 1 more
Abstract (arXiv)

Large language models (LLMs) undergo safety alignment after training and tuning, yet recent work shows that safety can be bypassed through jailbreak attacks. While many jailbreaks and defenses exist, their cross-lingual generalization remains underexplored. This paper presents the first systematic multilingual evaluation of jailbreaks and defenses across ten languages -- spanning high-, medium-, and low-resource languages -- using six LLMs on HarmBench and AdvBench. We assess two jailbreak types: logical-expression-based and adversarial-prompt-based. For both types, attack success and defense robustness vary across languages: high-resource languages are safer under standard queries but more vulnerable to adversarial ones. Simple defenses can be effective, but are language- and model-dependent. These findings call for language-aware and cross-lingual safety benchmarks for LLMs.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Safety alignment and jailbreak attacks, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 18 of its 29 references that are in the map. First posted on arXiv 1 Nov 2025.

Builds on

18 of 29 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025MPO: Multilingual Safety Alignment via Reward Gap Optimization22 May
  2. 2025Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical Expression18 May
  3. 2024How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States9 Jun
  4. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!5 Oct
  5. 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul

Other references · 13

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  4. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  5. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
  6. 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,326
  7. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 973
  8. 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 591
  9. 2021XLM-T: Multilingual Language Models in Twitter for Sentiment Analysis and Beyondcited by 114
  10. 2023Self-Guard: Empower the LLM to Safeguard Itselfcited by 52
  11. 2022An Analysis of Negation in Natural Language Understanding Corporacited by 39
  12. 2024Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understandingcited by 34
1 more
  1. 2024Nudging: Inference-time Alignment of LLMs via Guided Decodingcited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safetycited by 3
  2. 2026TukaBench: A Culturally Grounded Jailbreak Benchmark for African Languagescited by 3
  3. 2026SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speechcited by 0
  4. 2026LLM Safety Alignment in Low-Resource Languages: A Systematic Literature Reviewcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Jailbreak Attacks and Defenses Against Large Language Models: A Survey
  2. 2025PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
  3. 2025The Tower of Babel Revisited: Multilingual Jailbreak Prompts on Closed-Source Large Language Models
  4. 2025Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval
  5. 2024Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing
  6. 2024Playing Language Game with LLMs Leads to Jailbreaking
  7. 2026Analysis of LLMs Against Prompt Injection and Jailbreak Attacks
  8. 2026Minionese: Comprehensive Benchmark and Mechanistic Study of Multilingual LLM Safety