Restore safety in fine-tuned language models through task arithmetic

Repository for the Bias Benchmark for QA dataset.

Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Source code of "Reasons to Reject? Aligning Language Models with Judgments"

[ACL 2024] The official codebase for the paper "Self-Distillation Bridges Distribution Gap in Language Model Fine-tuning".

The Prism Alignment Project

Official Code for the papers: "Controlled Text Generation as Continuous Optimization with Multiple Constraints" and "Gradient-based Constrained Sampling from LMs"

Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model

[ACL 2024] Code for the paper "ALaRM: Align Language Models via Hierarchical Rewards Modeling"

WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning method which reduces LLM performance on WMDP while retaining …

最好用的 V2Ray 一键安装脚本 & 管理脚本

Controlled Text Generation via Language Model Arithmetic

Code for the ICLR 2023 paper: Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization

U.S. Congressional Tweets Dataset used in the ACL 2018 paper for predicting Moral Foundations of the tweets of U.S. politicians.

Released code for「Stance Detection on Social Media with Background Knowledge」in EMNLP2023.

Repository for the LREC 2022 submission on Emotion Word Dynamics in Geolocated Tweet data.

MLNLP社区用来帮助缩短参考文献的工具。A tool for simplifying bibtex with official info

Tips for paper writing and researches 科技论文写作经验记录和总结

MLNLP社区用来帮助大家避免论文投稿小错误的整理仓库。 Paper Writing Tips

Everything about note management. All in Zotero.

MLNLP: Paper Picture Writing Code

A curated list of Human Preference Datasets for LLM fine-tuning, RLHF, and eval.

Learning from Mistakes via Interactive Study Assistant for Large Language Models

This repository contains the dataset and codes for the task of Morality Frames prediction in political tweets using Relational Learning. This work is published as a paper - "Identifying Morality Fr…

Generative Agents: Interactive Simulacra of Human Behavior