# Self and Cross-Model Distillation for LLMs: Effective Methods for Refusal Pattern Alignment

arXiv: https://arxiv.org/abs/2406.11285 · HTML: https://mlsanity.com/paper/2406.11285/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment and jailbreak attacks, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 11 of its 21 references that are in the map.
- First posted on arXiv 17 Jun 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Safety alignment and jailbreak attacks](https://mlsanity.com/alignment/safety-alignment-and-jailbreak-attacks/)

## Builds on (most cited first, 11 of 11)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study](https://mlsanity.com/paper/2305.13860/) (2023)
- [Fine-Grained Human Feedback Gives Better Rewards for Language Model Training](https://mlsanity.com/paper/2306.01693/) (2023)
- [Pretraining Language Models with Human Preferences](https://mlsanity.com/paper/2302.08582/) (2023)
- [PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts](https://mlsanity.com/paper/2306.04528/) (2023)
- [How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition](https://mlsanity.com/paper/2310.05492/) (2023)
- [Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models](https://mlsanity.com/paper/2307.08487/) (2023)
- [Adversarial attacks and defenses in explainable artificial intelligence: A survey](https://mlsanity.com/paper/2306.06123/) (2023)
- [A Comprehensive Overview of Backdoor Attacks in Large Language Models within Communication Networks](https://mlsanity.com/paper/2308.14367/) (2023)

## Built on by (most cited first, 3 of 3)

- [OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs](https://mlsanity.com/paper/2601.01592/) (2026)
- [Characterizing Selective Refusal Bias in Large Language Models](https://mlsanity.com/paper/2510.27087/) (2025)
- [Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning](https://mlsanity.com/paper/2606.00105/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) like OpenAI's GPT series, Anthropic's Claude, and Meta's LLaMa have shown remarkable capabilities in text generation. However, their susceptibility to toxic prompts presents significant security challenges. This paper investigates alignment techniques, including Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), to mitigate these risks. We conduct an empirical study on refusal patterns across nine LLMs, revealing that models with uniform refusal patterns, such as Claude3, exhibit higher security. Based on these findings, we propose self-distilling and cross-model distilling methods to enhance LLM security. Our results show that these methods significantly improve refusal rates and reduce unsafe content, with cross-model distilling achieving refusal rates close to Claude3's 94.51%. These findings underscore the potential of distillation-based alignment in securing LLMs against toxic prompts.