AI-with-a-Conscience

Secrets of RLHF in Large Language Models Part I: PPO

PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. ? Best Paper Awards @ NeurIPS ML Safety Workshop 2022

[NeurIPS '23 Spotlight] Thought Cloning: Learning to Think while Acting by Imitating Human Thinking

RuLES: a benchmark for evaluating rule-following in language models

Code accompanying the paper Pretraining Language Models with Human Preferences

How to Make Safe AI? Let's Discuss! ?|?|?|?

Toolkits to create a human-in-the-loop approval layer to monitor and guide AI agents workflow in real-time.

Attack to induce LLMs within hallucinations

[ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use

BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).