README.md

---
license: apache-2.0
---
[**Paper**](https://openreview.net/pdf?id=jkcHYEfPv3)

[**Github**](https://github.com/declare-lab/red-instruct)

[**Dataset**](https://huggingface.co/datasets/declare-lab/HarmfulQA)

We created **Starling** by fine-tuning Vicuna-7B on HarmfulQA, a ChatGPT-distilled dataset that we collected using the Chain of Utterances (CoU) prompt. More details are on our paper [**Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment**](https://openreview.net/pdf?id=jkcHYEfPv3)

Experimental results on several safety benchmark datasets indicate that **Starling** is a safer model compared to the baseline model, Vicuna.

<img src="https://declare-lab.net/assets/images/logos/method.png" alt="Image" width="1000" height="335">

<h2>Experimental Results</h2>

**Compared to Vicuna, Avg. 5.2% reduction in Attack Success Rate (ASR) on DangerousQA and HarmfulQA using three different prompts.**

**Compared to Vicuna, Avg. 3-7% improvement in HHH score measured on BBH-HHH benchmark.**

<img src="https://declare-lab.net/assets/images/logos/starling-results.png" alt="Image" width="1000" height="335">

**TruthfulQA (MC2): 48.90 vs Vicuna's 47.00**

**MMLU (5-shot): 46.69 vs Vicuna's 47.18**

**BBH (3-shot): 33.47 vs Vicuna's 33.05**

<h2>Jailbreak Prompt for harmfulness eval using Red Eval as reported in the paper</h2>

**This jailbreak prompt (termed as Chain of Utterances (CoU) prompt in the paper) shows a 65% Attack Success Rate (ASR) on GPT-4 and 72% on ChatGPT.**

<img src="https://declare-lab.net/assets/images/logos/jailbreakprompt_main_paper.png" alt="Image" width="1000" height="1000">

<h2>HarmfulQA Data Collection</h2>

<img src="https://declare-lab.net/assets/images/logos/data_gen.png" alt="Image" width="1000" height="1000">

Note: This model is referred to as Starling (Blue) in the paper. We shall soon release Starling (Blue-Red) which was trained on harmful data using an objective function that helps model learn from the negative data.