3.7k citations · 10.2k across the 30 of their papers we have counts for
32 papers
A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity
Shayne Longpre, Gregory Yauney, Emily Reif +8
Pretraining is the preliminary and fundamental step in developing capable language models (LM). Despite this, pretraining data design is critically under-documented and often guide…
UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining
Hyung Won Chung, Noah Constant, Xavier Garcia +4
Pretrained multilingual large language models have typically used heuristic temperature-based sampling to balance between different languages. However previous work has not systema…
The Flan Collection: Designing Data and Methods for Effective Instruction Tuning
Shayne Longpre, Le Hou, Tu Vu +8
We study the design decisions of publicly available instruction tuning methods, and break down the development of Flan 2022 (Chung et al., 2022). Through careful ablation studies o…
Character-Aware Models Improve Visual Text Rendering
Rosanne Liu, Dan Garrette, Chitwan Saharia +7
Current image generation models struggle to reliably produce well-formed visual text. In this paper, we investigate a key contributing factor: popular text-to-image models lack cha…
VeLO: Training Versatile Learned Optimizers by Scaling Up
Luke Metz, James Harrison, C. Daniel Freeman +8
While deep learning models have replaced hand-designed features across many domains, these models are still trained with hand-designed optimizers. In this work, we leverage the sam…
Large Language Models Struggle to Learn Long-Tail Knowledge
Nikhil Kandpal, Haikang Deng, Adam Roberts +2
The Internet contains a wealth of knowledge -- from the birthdays of historical figures to tutorials on how to code -- all of which may be learned by language models. However, whil…
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
BigScience Workshop, :, Teven Le Scao +391
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to wi…
Crosslingual Generalization through Multitask Finetuning
Niklas Muennighoff, Thomas Wang, Lintang Sutawika +16
Multitask prompted finetuning (MTF) has been shown to help large language models generalize to new tasks in a zero-shot setting, but so far explorations of MTF have focused on Engl…
Scaling Instruction-Finetuned Language Models
Hyung Won Chung, Le Hou, Shayne Longpre +32
Finetuning language models on a collection of datasets phrased as instructions has been shown to improve model performance and generalization to unseen tasks. In this paper we expl…
What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?
Thomas Wang, Adam Roberts, Daniel Hesslow +5
Large pretrained Transformer language models have been shown to exhibit zero-shot generalization, i.e. they can perform a wide variety of tasks that they were not explicitly traine…
PaLM: Scaling Language Modeling with Pathways
Aakanksha Chowdhery, Sharan Narang, Jacob Devlin +64
Large language models have been shown to achieve remarkable performance across a variety of natural language tasks using few-shot learning, which drastically reduces the number of…
Scaling Up Models and Data with and
Adam Roberts, Hyung Won Chung, Anselm Levskaya +40
Recent neural network-based language models have benefited greatly from scaling up the size of training datasets and the number of parameters in the models themselves. Scaling can…
LaMDA: Language Models for Dialog Applications
Romal Thoppilan, Daniel De Freitas, Jamie Hall +57
We present LaMDA: Language Models for Dialog Applications. LaMDA is a family of Transformer-based neural language models specialized for dialog, which have up to 137B parameters an…
ByT5: Towards a token-free future with pre-trained byte-to-byte models
Linting Xue, Aditya Barua, Noah Constant +5
Most widely-used pre-trained language models operate on sequences of tokens corresponding to word or subword units. By comparison, token-free models that operate directly on raw te…
Do Transformer Modifications Transfer Across Implementations and Applications?
Sharan Narang, Hyung Won Chung, Yi Tay +13
The research community has proposed copious modifications to the Transformer architecture since it was introduced over three years ago, relatively few of which have seen widespread…
NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
Sewon Min, Jordan Boyd-Graber, Chris Alberti +50
We review the EfficientQA competition from NeurIPS 2020. The competition focused on open-domain question answering (QA), where systems take natural language questions as input and…
Extracting Training Data from Large Language Models
Nicholas Carlini, Florian Tramer, Eric Wallace +9
It has become common to publish large (billion parameter) language models that have been trained on private datasets. This paper demonstrates that in such settings, an adversary ca…
mT5: A massively multilingual pre-trained text-to-text transformer
Linting Xue, Noah Constant, Adam Roberts +5
The recent "Text-to-Text Transfer Transformer" (T5) leveraged a unified text-to-text format and scale to attain state-of-the-art results on a wide variety of English-language NLP t…
WT5?! Training Text-to-Text Models to Explain their Predictions
Sharan Narang, Colin Raffel, Katherine Lee +3
Neural networks have recently achieved human-level performance on various challenging natural language processing (NLP) tasks, but it is notoriously difficult to understand why a n…
How Much Knowledge Can You Pack Into the Parameters of a Language Model?
Adam Roberts, Colin Raffel, Noam Shazeer
It has recently been observed that neural language models trained on unstructured text can implicitly store and retrieve knowledge using natural language queries. In this short pap…
DDSP: Differentiable Digital Signal Processing
Jesse Engel, Lamtharn Hantrakul, Chenjie Gu +1
Most generative models of audio directly generate samples in one of two domains: time or frequency. While sufficient to express any signal, these representations are inefficient, a…
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Colin Raffel, Noam Shazeer, Adam Roberts +6
Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language proc…
The Bach Doodle: Approachable music composition with machine learning at scale
Cheng-Zhi Anna Huang, Curtis Hawthorne, Adam Roberts +4
To make music composition more approachable, we designed the first AI-powered Google Doodle, the Bach Doodle, where users can create their own melody and have it harmonized by a ma…
Learning to Groove with Inverse Sequence Transformations
Jon Gillick, Adam Roberts, Jesse Engel +2
We explore models for translating abstract musical ideas (scores, rhythms) into expressive performances using Seq2Seq and recurrent Variational Information Bottleneck (VIB) models.…