Lists (6)
Stars
🔥 Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation 🔥. Our toolkit integrates 40 pre-retrieved benchmark datasets and supports 7+ retrieval techn…
Anserini is a Lucene toolkit for reproducible information retrieval research
Data and code for APPDIA: A Discourse-aware Transformer-based Style Transfer Model for Offensive Social Media Conversations (COLING 2022).
Data and info for the paper "ParaDetox: Text Detoxification with Parallel Data"
Repository for ACL 2022 paper Mix and Match: Learning-free Controllable Text Generation using Energy Language Models
Official repository of "Controlled Text Generation for Black-box Language Models via Score-based Progressive Editor" (ACL 2024 main)
See https://meta.wikimedia.org/wiki/Research:Modeling_Talk_Page_Abuse
Repository for the paper "Automated Hate Speech Detection and the Problem of Offensive Language", ICWSM 2017
Datasets for Hate Speech Detection
Data for evaluating gender bias in coreference resolution systems.
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
This repo includes ChatGPT prompt curation to use ChatGPT and other LLM tools better.
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama mode…
ACL 2022: An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models.
EMNLP'2021: Simple Entity-centric Questions Challenge Dense Retrievers https://arxiv.org/abs/2109.08535
ICML'2022: Black-Box Tuning for Language-Model-as-a-Service & EMNLP'2022: BBTv2: Towards a Gradient-Free Future with Large Language Models
A beautiful, simple, clean, and responsive Jekyll theme for academics
Library for Knowledge Intensive Language Tasks
🦜🔗 Build context-aware reasoning applications
EMNLP'2022: BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation
GAP is a gender-balanced dataset containing 8,908 coreference-labeled pairs of (ambiguous pronoun, antecedent name), sampled from Wikipedia for the evaluation of coreference resolution in practica…
Dataset associated with "BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation" paper
Repository for research in the field of Responsible NLP at Meta.
Paper collections of retrieval-based (augmented) language model.
Supercharge Your LLM Application Evaluations 🚀
A new markup-based typesetting system that is powerful and easy to learn.
A simple and elegant Jekyll theme for an academic personal homepage