zhentingqi

attack-via-GCG

Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives

auto-dan

The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models".

instruct-eval

This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.

length-generalization

Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023

lost-in-the-middle

Code and data for "Lost in the Middle: How Language Models Use Long Contexts"

Math_LLM

Code for MIT 6.8610 project

probing

Program-of-Thoughts

Data and Code for Program of Thoughts (TMLR 2023)

rag-privacy

representation-engineering

Representation Engineering: A Top-Down Approach to AI Transparency

zhentingqi/attack-via-GCG

Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives

zhentingqi/auto-dan

The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models".

zhentingqi/instruct-eval

This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.

zhentingqi/length-generalization

Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023

zhentingqi/lost-in-the-middle

Code and data for "Lost in the Middle: How Language Models Use Long Contexts"

zhentingqi/Math_LLM

Code for MIT 6.8610 project

zhentingqi/probing

zhentingqi/Program-of-Thoughts

Data and Code for Program of Thoughts (TMLR 2023)

zhentingqi/rag-privacy

zhentingqi/representation-engineering

Representation Engineering: A Top-Down Approach to AI Transparency

zhentingqi/ushape

zhentingqi/zhentingqi-past.github.io

Personal Webpage

zhentingqi/zhentingqi.github.io