Code and data for "Measuring and Narrowing the Compositionality Gap in Language Models"

FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)

LLaMa retrieval plugin script using OpenAI's retrieval plugin

Fusion-in-Decoder

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

A codebase that makes differentially private training of transformers easy.

Reproduce results and replicate training fo T0 (Multitask Prompted Training Enables Zero-Shot Task Generalization)

An Empirical Evaluation of Word Embedding Models for Subjectivity Analysis Tasks

Few-shot Learning of GPT-3

Google Research

FaVIQ: Fact Verification from Information-seeking Questions

Adversarial Natural Language Inference Benchmark

Methods of training NLP models to ignored biased strategies

Hyperbolic Graph Neural Networks

Resources for the MRQA 2019 Shared Task

A simple way to calibrate your neural network.

Binary Classifier Calibration Models

Code for the paper "SelectiveNet: A Deep Neural Network with an Integrated Reject Option"

Implementation of various SQuAD models