HUJA9

alignment-handbook

Robust recipes to align language models with human and AI preferences

Bag-of-Tricks-for-AT

Empirical tricks for training robust models (ICLR 2021)

aligner

Achieving Efficient Alignment through Learned Correction

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

lime

Lime: Explaining the predictions of any machine learning classifier

safe-rlhf

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

OpenBackdoor

An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)

BackdoorBench

PromptAttack

An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)

llm-attacks

Universal and Transferable Attacks on Aligned Language Models

ToolBench

[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.

llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

LLMs-Finetuning-Safety

We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20 via OpenAI’s APIs.

LLM-Conversation-Safety

[NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey

Trojan-Activation-Attack

LM-exp

LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces

swa_gaussian

Code repo for "A Simple Baseline for Bayesian Uncertainty in Deep Learning"

transferlearning

Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

corr2cause

Data and code for the Corr2Cause paper (ICLR 2024)

Causality4NLP_Papers

A reading list for papers on causality for natural language processing (NLP)

causal-text-papers

Curated research at the intersection of causal inference and natural language processing.

causalml

Uplift modeling and causal inference with machine learning algorithms

dowhy

DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphical models and potential outcomes frameworks.

Awesome-LLM-Interpretability

A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..

DoLa

Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"

DecodingTrust

A Comprehensive Assessment of Trustworthiness in GPT Models

TrustLLM

[ICML 2024] TrustLLM: Trustworthiness in Large Language Models

awesome-instruction-dataset

A collection of open-source dataset to train instruction-following LLMs (ChatGPT,LLaMA,Alpaca)

natural-instructions

Expanding natural instructions