# DiveR-CT: Diversity-enhanced Red Teaming Large Language Model Assistants with Relaxing Constraints

arXiv: https://arxiv.org/abs/2405.19026 · HTML: https://mlsanity.com/paper/2405.19026/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Prompt injection and agent security, one of 12 directions in LLM safety and security.
- First posted on arXiv 29 May 2024.

## Placed in

- LLM safety and security / [Prompt injection and agent security](https://mlsanity.com/safety/prompt-injection-and-agent-security/)

## Built on by (most cited first, 10 of 10)

- [Absolute Zero: Reinforced Self-play Reasoning with Zero Data](https://mlsanity.com/paper/2505.03335/) (2025)
- [Yi-Lightning Technical Report](https://mlsanity.com/paper/2412.01253/) (2024)
- [TEAR: Temporal-aware Automated Red-teaming for Text-to-Video Models](https://mlsanity.com/paper/2511.21145/) (2025)
- [Scaffolded Language Models with Language Supervision for Mixed-Autonomy: A Survey](https://mlsanity.com/paper/2410.16392/) (2024)
- [Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers](https://mlsanity.com/paper/2510.14381/) (2025)
- [RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming](https://mlsanity.com/paper/2506.04302/) (2025)
- [OptiLeak: Efficient Prompt Reconstruction via Reinforcement Learning in Multi-tenant LLM Services](https://mlsanity.com/paper/2602.20595/) (2026)
- [Malicious Repurposing of Open Science Artefacts by Using Large Language Models](https://mlsanity.com/paper/2601.18998/) (2026)
- [A Systematic Investigation of RL-Jailbreaking in LLMs](https://mlsanity.com/paper/2605.07032/) (2026)
- [The Safeguard Worked. Is the LLM System Safer?](https://mlsanity.com/paper/2609.00519/) (2026)

## Abstract (arXiv)

Recent advances in large language model assistants have made them indispensable, raising significant concerns over managing their safety. Automated red teaming offers a promising alternative to the labor-intensive and error-prone manual probing for vulnerabilities, providing more consistent and scalable safety evaluations. However, existing approaches often compromise diversity by focusing on maximizing attack success rate. Additionally, methods that decrease the cosine similarity from historical embeddings with semantic diversity rewards lead to novelty stagnation as history grows. To address these issues, we introduce DiveR-CT, which relaxes conventional constraints on the objective and semantic reward, granting greater freedom for the policy to enhance diversity. Our experiments demonstrate DiveR-CT's marked superiority over baselines by 1) generating data that perform better in various diversity metrics across different attack success rate levels, 2) better-enhancing resiliency in blue team models through safety tuning based on collected data, 3) allowing dynamic control of objective weights for reliable and controllable attack success rates, and 4) reducing susceptibility to reward overoptimization. Overall, our method provides an effective and efficient approach to LLM red teaming, accelerating real-world deployment.