Challenge: Large language models (LLMs) are still vulnerable to generation safety vulnerabilities.
Approach: They propose a method that A**tacks LLMs with target "toxi" given a particular harmful answer, the method generates a user query and a misleading answer opening to examine the internal defects of a given LLM.
Outcome: The proposed method detects safety risks in open-source models and state-of-the-art models such as GPT-4o.

Similar Papers

Holistic Automated Red Teaming for Large Language Models through Top-Down Test Case Generation and Multi-turn Interaction (2024.emnlp-main)

Copied to clipboard

Challenge: Existing approaches focus on improving attack success rates while overlooking the need for comprehensive test case coverage.
Approach: They propose a top-down approach to automated red teaming that scales up the diversity of test cases using an extensible, fine-grained risk taxonomy.
Outcome: The proposed approach scales up the diversity of test cases using a top-down approach based on an extensible, fine-grained risk taxonomy and leverages reinforcement learning techniques to facilitate multi-turn adversarial probing in a human-like manner.
When Prompt Optimization Becomes Jailbreaking: Adaptive Red-Teaming of Large Language Models (2026.eacl-srw)

Copied to clipboard

Challenge: Existing safety evaluations rely on fixed collections of harmful prompts . such attacks span single-shot prompts, multi-turn interactions, cross-lingual settings .
Approach: They propose to use black-box prompt optimization techniques to search for safety failures . they use GPT-5.1 to optimize for a continuous danger score .
Outcome: The proposed approach reduces effective safeguards for large language models . the average danger score of Qwen 3 8B increases from 0.09 in its baseline setting to 0.79 after optimization.
Red Teaming Language Models with Language Models (2022.emnlp-main)

Copied to clipboard

Challenge: Prior work has found that language models (LMs) can harm users in hard-to-predict ways, and human annotation is expensive, limiting the number and diversity of test cases.
Approach: They propose to generate test inputs using an LM itself, and use a classifier to detect harmful behavior on test input.
Outcome: The proposed approach detects tens of thousands of offensive responses in a 280B parameter LM chatbot.
RedCoder: Automated Multi-Turn Red Teaming for Code LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing red-teaming approaches for code generation rely on extensive human effort and are prone to generating malicious code under adversarial environments.
Approach: They propose a red-teaming agent that engages victim models in multi-turn conversations to elicit vulnerable code.
Outcome: Experiments show that RedCoder outperforms red-teaming methods in inducing vulnerabilities in code generation.
Toxicity Red-Teaming: Benchmarking LLM Safety in Singapore’s Low-Resource Languages (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have transformed natural language processing, but their safety mechanisms remain under-explored in low-resource, multilingual settings.
Approach: They propose a red-teaming approach to probe LLM vulnerabilities in Singapore's diverse linguistic context using a dataset and evaluation framework.
Outcome: The proposed framework systematically probes LLM vulnerabilities in three real-world scenarios including Singlish, Chinese, Malay, and Tamil.
Automated Progressive Red Teaming (2025.coling-main)

Copied to clipboard

Challenge: Automated red teaming (ART) is effective but time-consuming, costly and lacks scalability.
Approach: They propose an automated red teaming framework that generates adversarial prompts to expose LLM vulnerabilities.
Outcome: The proposed framework explores and exploits LLM vulnerabilities through multi-round interactions.
Attack Prompt Generation for Red Teaming and Defending Large Language Models (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing studies construct attack prompts via manual or automatic methods, but these methods have limitations on cost and quality.
Approach: They propose an attack framework to instruct LLMs to mimic human-generated prompts through in-context learning and a defense framework that fine-tunes victim LLM's through iterative interactions with the attack framework.
Outcome: The proposed approach is based on experiments on different LLMs to evaluate their effectiveness against red teaming attacks.
Gradient-Based Language Model Red Teaming (2024.eacl-long)

Copied to clipboard

Challenge: generative language models generate unsafe responses by producing adversarial prompts . red teaming is labor-intensive and difficult to scale when done by humans.
Approach: They propose a red teaming method that generates diverse prompts that are likely to cause an LM to generate unsafe responses.
Outcome: The proposed method is more effective at finding prompts that trigger an LM to generate unsafe responses than a strong reinforcement learning-based red teaming approach.
Distract Large Language Models for Automatic Jailbreak Attack (2024.emnlp-main)

Copied to clipboard

Challenge: Commercial large language models (LLMs) have made great progress in various NLP tasks.
Approach: They propose a black-box jailbreak framework for automated red teaming of Large language models using an iterative optimization algorithm to conceal malicious content and memory reframing.
Outcome: The proposed framework outperforms existing jailbreak defense methods and highlights the need to develop more effective and practical defense strategies.
ToxiPrompt: A Two-Stage Red-Teaming Approach for Balancing Adversarial Prompt Diversity and Response Toxicity (2026.eacl-long)

Copied to clipboard

Challenge: Large language models (LLMs) pose safety risks, but current redteaming methods rely on human testers manually designing adversarial prompts.
Approach: They propose a red-teaming method that generates adversarial prompts to elicit unsafe behavior of target LLMs.
Outcome: The proposed approach outperforms state-of-the-art methods in diversity and toxicity . it performs well for multiple instruction-tuned target LLMs without re-tuning .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations