Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture

• URL: http://arxiv.org/abs/2407.07342v1
• Date: Wed, 10 Jul 2024 03:26:15 GMT
• Title: Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture
• Authors: Jiayang Song, Yuheng Huang, Zhehua Zhou, Lei Ma,
• Abstract summary: We introduce Multilingual Blending, a mixed-language query-response scheme designed to evaluate the safety alignment of various large language models. We investigate language patterns such as language availability, morphology, and language family that could impact the effectiveness of Multilingual Blending.
• Score: 6.17896401271963
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As safety remains a crucial concern throughout the development lifecycle of Large Language Models (LLMs), researchers and industrial practitioners have increasingly focused on safeguarding and aligning LLM behaviors with human preferences and ethical standards. LLMs, trained on extensive multilingual corpora, exhibit powerful generalization abilities across diverse languages and domains. However, current safety alignment practices predominantly focus on single-language scenarios, which leaves their effectiveness in complex multilingual contexts, especially for those complex mixed-language formats, largely unexplored. In this study, we introduce Multilingual Blending, a mixed-language query-response scheme designed to evaluate the safety alignment of various state-of-the-art LLMs (e.g., GPT-4o, GPT-3.5, Llama3) under sophisticated, multilingual conditions. We further investigate language patterns such as language availability, morphology, and language family that could impact the effectiveness of Multilingual Blending in compromising the safeguards of LLMs. Our experimental results show that, without meticulously crafted prompt templates, Multilingual Blending significantly amplifies the detriment of malicious queries, leading to dramatically increased bypass rates in LLM safety alignment (67.23% on GPT-3.5 and 40.34% on GPT-4o), far exceeding those of single-language baselines. Moreover, the performance of Multilingual Blending varies notably based on intrinsic linguistic properties, with languages of different morphology and from diverse families being more prone to evading safety alignments. These findings underscore the necessity of evaluating LLMs and developing corresponding safety alignment strategies in a complex, multilingual context to align with their superior cross-language generalization capabilities.

Related papers

• Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models [62.91524967852552]
  Large language models (LLMs) are typically multilingual due to pretraining on diverse multilingual corpora. But can these models relate corresponding concepts across languages, effectively being crosslingual? This study evaluates six state-of-the-art LLMs on inherently crosslingual tasks.
  arXiv  Detail & Related papers  (2024-06-23T15:15:17Z)
• Teaching LLMs to Abstain across Languages via Multilingual Feedback [40.84205285309612]
  We show that multilingual feedback helps identify knowledge gaps across diverse languages, cultures, and communities. Extensive experiments demonstrate that our multilingual feedback approach outperforms various strong baselines. Further analysis reveals that multilingual feedback is both an effective and a more equitable abstain strategy to serve diverse language speakers.
  arXiv  Detail & Related papers  (2024-06-22T21:59:12Z)
• Towards Truthful Multilingual Large Language Models: Benchmarking and Alignment Strategies [38.3269908062146]
  We construct a benchmark for truthfulness evaluation in multilingual scenarios. We propose Fact-aware Multilingual Selective Synergy (FaMSS) to optimize the data allocation across a large number of languages.
  arXiv  Detail & Related papers  (2024-06-20T15:59:07Z)
• Getting More from Less: Large Language Models are Good Spontaneous Multilingual Learners [67.85635044939836]
  Large Language Models (LLMs) have shown impressive language capabilities. In this work, we investigate the spontaneous multilingual alignment improvement of LLMs. We find that LLMs instruction-tuned on the question translation data (i.e. without annotated answers) are able to encourage the alignment between English and a wide range of languages.
  arXiv  Detail & Related papers  (2024-05-22T16:46:19Z)
• Exploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages? [34.38469832305664]
  We explore 7 types of human values, 16 languages and 3 LLM series with distinct multilinguality. Cross-lingual analysis on these concepts discloses 3 traits arising from language resource disparities. We provide suggestions on the composition of multilingual data for LLMs pre-training.
  arXiv  Detail & Related papers  (2024-02-28T07:18:39Z)
• Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models [117.20416338476856]
  Large language models (LLMs) demonstrate remarkable multilingual capabilities without being pre-trained on specially curated multilingual parallel corpora. We propose a novel detection method, language activation probability entropy (LAPE), to identify language-specific neurons within LLMs. Our findings indicate that LLMs' proficiency in processing a particular language is predominantly due to a small subset of neurons.
  arXiv  Detail & Related papers  (2024-02-26T09:36:05Z)
• The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts [46.089025223336854]
  This paper examines the variations in safety challenges faced by large language models across different languages. We compare how state-of-the-art LLMs respond to the same set of malicious prompts written in higher- vs. lower-resource languages.
  arXiv  Detail & Related papers  (2024-01-23T23:12:09Z)
• Multilingual Jailbreak Challenges in Large Language Models [96.74878032417054]
  In this study, we reveal the presence of multilingual jailbreak challenges within large language models (LLMs) We consider two potential risky scenarios: unintentional and intentional. We propose a novel textscSelf-Defense framework that automatically generates multilingual training data for safety fine-tuning.
  arXiv  Detail & Related papers  (2023-10-10T09:44:06Z)
• All Languages Matter: On the Multilingual Safety of Large Language Models [96.47607891042523]
  We build the first multilingual safety benchmark for large language models (LLMs) XSafety covers 14 kinds of commonly used safety issues across 10 languages that span several language families. We propose several simple and effective prompting methods to improve the multilingual safety of ChatGPT.
  arXiv  Detail & Related papers  (2023-10-02T05:23:34Z)
• Breaking Language Barriers with a LEAP: Learning Strategies for Polyglot LLMs [5.682384717239095]
  Large language models (LLMs) are at the forefront of transforming numerous domains globally. This paper tackles the imperative challenge of enhancing the multilingual performance of LLMs. We present novel techniques that unlock the true potential of LLMs in a polyglot landscape.
  arXiv  Detail & Related papers  (2023-05-28T14:48:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.