NLP

Research

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

December 16, 2020

Abstract

Large pre-trained language models have been shown to store factual knowledge in their parameters, and achieve state-of-the-art results when fine-tuned on downstream NLP tasks. However, their ability to access and precisely manipulate knowledge is still limited, and hence on knowledge-intensive tasks, their performance lags behind task-specific architectures. Additionally, providing provenance for their decisions and updating their world knowledge remain open research problems. Pre-trained models with a differentiable access mechanism to explicit non-parametric memory can overcome this issue, but have so far been only investigated for extractive downstream tasks. We explore a general-purpose fine-tuning recipe for retrieval-augmented generation (RAG) -- models which combine pre-trained parametric and non-parametric memory for language generation. We introduce RAG models where the parametric memory is a pre-trained seq2seq model and the non-parametric memory is a dense vector index of Wikipedia, accessed with a pre-trained neural retriever. We compare two RAG formulations, one which conditions on the same retrieved passages across the whole generated sequence, the other can use different passages per token. We fine-tune and evaluate our models on a wide range of knowledge-intensive NLP tasks and set the state-of-the-art on three open domain QA tasks, outperforming parametric seq2seq models and task-specific retrieve-and-extract architectures. For language generation tasks, we find that RAG models generate more specific, diverse and factual language than a state-of-the-art parametric-only seq2seq baseline.

Download the Paper

AUTHORS

Written by

Patrick Lewis

Ethan Perez

Aleksandra Piktus

Fabio Petroni

Vladimir Karpukhin

Naman Goyal

Heinrich Küttler

Mike Lewis

Wen-tau Yih

Tim Rocktäschel

Sebastian Riedel

Douwe Kiela

Publisher

NeurIPS 2020

Related Publications

November 16, 2022

NLP

Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models

Kushal Tirumala, Aram H. Markosyan, Armen Aghajanyan, Luke Zettlemoyer

November 16, 2022

October 31, 2022

NLP

Autoregressive Search Engines: Generating Substrings as Document Identifiers

Fabio Petroni, Giuseppe Ottaviano, Michele Bevilacqua, Patrick Lewis, Scott Yih, Sebastian Riedel

October 31, 2022

December 06, 2020

NLP

Pre-training via Paraphrasing

Michael Lewis, Armen Aghajanyan, Gargi Ghosh, Luke Zettlemoyer, Marjan Ghazvininejad, Sida Wang

December 06, 2020

November 30, 2020

NLP

Where Are You? Localization from Embodied Dialog

Dhruv Batra, Devi Parikh, Meera Hahn, Jacob Krantz, James Rehg, Peter Anderson, Stefan Lee

November 30, 2020

April 30, 2018

NLP

Speech & Audio

Identifying Analogies Across Domains | Facebook AI Research

Yedid Hoshen, Lior Wolf

April 30, 2018

November 01, 2018

NLP

Computer Vision

Non-Adversarial Unsupervised Word Translation | Facebook AI Research

Yedid Hoshen, Lior Wolf

November 01, 2018

December 02, 2018

NLP

Computer Vision

One-Shot Unsupervised Cross Domain Translation | Facebook AI Research

Sagie Benaim, Lior Wolf

December 02, 2018

June 30, 2019

NLP

Variational Training for Large-Scale Noisy-OR Bayesian Networks | Facebook AI Research

Geng Ji, Dehua Cheng, Huazhong Ning, Changhe Yuan, Hanning Zhou, Liang Xiong, Erik B. Sudderth

June 30, 2019

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.