An Open Robustness Benchmark for Jailbreaking Language Models [arXiv 2024]

Fast and accurate Active SAmpling method for Pairwise comparisons

Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

A Benchmark of Text Classification in PyTorch

MAD: The first work to explore Multi-Agent Debate with Large Language Models :D

Minimalist ML framework for Rust

Official reposity for paper "High-Dimension Human Value Representation in Large Language Models"

SimPO: Simple Preference Optimization with a Reference-Free Reward

Extraction of the Schwartz 10 human values + 4 high-order values from the PVQ(ESS) 21 questionnaire

🥨 Lobe Icons - Popular AI / LLM Model Brand SVG Logo and Icon Collection.

Croissant is a high-level format for machine learning datasets that brings together four rich layers.

Library of contextual bandits algorithms

Python implementations of contextual bandits algorithms

RewardBench: the first evaluation tool for reward models.

FMA: A Dataset For Music Analysis

Code for "Goodtriever: Toxicity Mitigation with Retrieval-augmented Language Models"

Semi-Offline Reinforcement Learning for Optimized Text Generation

Inference Llama 2 in one file of pure C

The simplest, fastest repository for training/finetuning medium-sized GPTs.

This repository introduces MentaLLaMA, the first open-source instruction following large language model for interpretable mental health analysis.

The official repository of "Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint"

Acceptance rates for the major AI conferences

About The official GitHub page for ''Unleashing the Potential of Large Language Models as Prompt Optimizers: An Analogical Analysis with Gradient-based Model Optimizers'' Resources

Official implementation of the paper "ConPrompt: Pre-training a Language Model with Machine-Generated Data for Implicit Hate Speech Detection" (Findings of EMNLP 2023)