Multi-lingual Multi-turn Automated Red Teaming for LLMs

• URL: http://arxiv.org/abs/2504.03174v1
• Date: Fri, 04 Apr 2025 05:06:12 GMT
• Title: Multi-lingual Multi-turn Automated Red Teaming for LLMs
• Authors: Abhishek Singhania, Christophe Dupuy, Shivam Mangale, Amani Namboori,
• Abstract summary: Multi-lingual Multi-turn Automated Red Teaming (textbfMM-ART) is a method to fully automate conversational, multi-lingual red-teaming operations.<n>We show the studied LLMs are on average 71% more vulnerable after a 5-turn conversation in English than after the initial turn.<n>For conversations in non-English languages, models display up to 195% more safety vulnerabilities than the standard single-turn English approach.
• Score: 4.707861373629172
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Language Model Models (LLMs) have improved dramatically in the past few years, increasing their adoption and the scope of their capabilities over time. A significant amount of work is dedicated to ``model alignment'', i.e., preventing LLMs to generate unsafe responses when deployed into customer-facing applications. One popular method to evaluate safety risks is \textit{red-teaming}, where agents attempt to bypass alignment by crafting elaborate prompts that trigger unsafe responses from a model. Standard human-driven red-teaming is costly, time-consuming and rarely covers all the recent features (e.g., multi-lingual, multi-modal aspects), while proposed automation methods only cover a small subset of LLMs capabilities (i.e., English or single-turn). We present Multi-lingual Multi-turn Automated Red Teaming (\textbf{MM-ART}), a method to fully automate conversational, multi-lingual red-teaming operations and quickly identify prompts leading to unsafe responses. Through extensive experiments on different languages, we show the studied LLMs are on average 71\% more vulnerable after a 5-turn conversation in English than after the initial turn. For conversations in non-English languages, models display up to 195\% more safety vulnerabilities than the standard single-turn English approach, confirming the need for automated red-teaming methods matching LLMs capabilities.

Related papers

• MR. Guard: Multilingual Reasoning Guardrail using Curriculum Learning [56.79292318645454]
  Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking. This vulnerability is exacerbated in multilingual setting, where multilingual safety-aligned data are often limited. We propose an approach to build a multilingual guardrail with reasoning.
  arXiv  Detail & Related papers  (2025-04-21T17:15:06Z)
• Think Carefully and Check Again! Meta-Generation Unlocking LLMs for Low-Resource Cross-Lingual Summarization [108.6908427615402]
  Cross-lingual summarization ( CLS) aims to generate a summary for the source text in a different target language.<n>Currently, instruction-tuned large language models (LLMs) excel at various English tasks.<n>Recent studies have shown that LLMs' performance on CLS tasks remains unsatisfactory even with few-shot settings.
  arXiv  Detail & Related papers  (2024-10-26T00:39:44Z)
• Arondight: Red Teaming Large Vision Language Models with Auto-generated Multi-modal Jailbreak Prompts [25.661444231400772]
  Large Vision Language Models (VLMs) extend and enhance the perceptual abilities of Large Language Models (LLMs) These advancements raise significant security and ethical concerns, particularly regarding the generation of harmful content. We introduce Arondight, a standardized red team framework tailored specifically for VLMs.
  arXiv  Detail & Related papers  (2024-07-21T04:37:11Z)
• 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.<n>But can these models relate corresponding concepts across languages, i.e., be crosslingual?<n>This study evaluates state-of-the-art LLMs on inherently crosslingual tasks.
  arXiv  Detail & Related papers  (2024-06-23T15:15:17Z)
• Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding [10.154013836043816]
  Code-switching in red-teaming queries can effectively elicit undesirable behaviors of large language models (LLMs) We introduce a simple yet effective framework, CSRT, to synthesize code-switching red-teaming queries. We demonstrate that the CSRT significantly outperforms existing multilingual red-teaming techniques.
  arXiv  Detail & Related papers  (2024-06-17T06:08:18Z)
• Curiosity-driven Red-teaming for Large Language Models [43.448044721642916]
  Large language models (LLMs) hold great potential for many natural language applications but risk generating incorrect or toxic content. relying solely on human testers is expensive and time-consuming. Our method of curiosity-driven red teaming (CRT) achieves greater coverage of test cases while mantaining or increasing their effectiveness compared to existing methods.
  arXiv  Detail & Related papers  (2024-02-29T18:55:03Z)
• Gradient-Based Language Model Red Teaming [9.972783485792885]
  Red teaming is a strategy for identifying weaknesses in generative language models (LMs) Red teaming is instrumental for both model alignment and evaluation, but is labor-intensive and difficult to scale when done by humans. We present Gradient-Based Red Teaming (GBRT), a red teaming method for automatically generating diverse prompts that are likely to cause an LM to output unsafe responses.
  arXiv  Detail & Related papers  (2024-01-30T01:19:25Z)
• 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)
• LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models [56.25156596019168]
  This paper introduces the LMRL-Gym benchmark for evaluating multi-turn RL for large language models (LLMs) Our benchmark consists of 8 different language tasks, which require multiple rounds of language interaction and cover a range of tasks in open-ended dialogue and text games.
  arXiv  Detail & Related papers  (2023-11-30T03:59:31Z)
• 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)
• Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts [75.33019401706188]
  Large language models (LLMs) are known to effectively perform tasks by simply observing few exemplars. We propose to assemble synthetic exemplars from a diverse set of high-resource languages to prompt the LLMs to translate from any language into English. Our unsupervised prompting method performs on par with supervised few-shot learning in LLMs of different sizes for translations between English and 13 Indic and 21 African low-resource languages.
  arXiv  Detail & Related papers  (2023-06-20T08:27:47Z)

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.