Arrow Research search

Author name cluster

Colin Raffel

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

33 papers
2 author rows

Possible papers

33

TMLR Journal 2025 Journal Article

A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning

  • Prateek Yadav
  • Colin Raffel
  • Mohammed Muqeeth
  • Lucas Caccia
  • Haokun Liu
  • Tianlong Chen
  • Mohit Bansal
  • Leshem Choshen

The availability of performant pre-trained models has led to a proliferation of fine-tuned expert models that are specialized to a particular domain or task. Model MoErging methods aim to recycle expert models to create an aggregate system with improved performance or generalization. A key component of MoErging methods is the creation of a router that decides which expert model(s) to use for a particular input or application. The promise, effectiveness, and large design space of MoErging has spurred the development of many new methods over the past few years. This rapid pace of development has made it challenging to compare different MoErging methods, which are rarely compared to one another and are often validated in different experimental setups. To remedy such gaps, we present a comprehensive survey of MoErging methods that includes a novel taxonomy for cataloging key design choices and clarifying suitable applications for each method. Apart from surveying MoErging research, we inventory software tools and applications that make use of MoErging. We additionally discuss related fields of study such as model merging, multitask learning, and mixture-of-experts models. Taken as a whole, our survey provides a unified overview of existing MoErging methods and creates a solid foundation for future work in this burgeoning field.

PDF Details

ICLR Conference 2025 Conference Paper

AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution

  • Fengyuan Liu
  • Nikhil Kandpal
  • Colin Raffel

The influence of contextual input on the behavior of large language models (LLMs) has prompted the development of context attribution methods that aim to quantify each context span's effect on an LLM's generations. The leave-one-out (LOO) error, which measures the change in the likelihood of the LLM's response when a given span of the context is removed, provides a principled way to perform context attribution, but can be prohibitively expensive to compute for large models. In this work, we introduce AttriBoT, a series of novel techniques for efficiently computing an approximation of the LOO error for context attribution. Specifically, AttriBoT uses cached activations to avoid redundant operations, performs hierarchical attribution to reduce computation, and emulates the behavior of large target models with smaller proxy models. Taken together, AttriBoT can provide a 300x speedup while remaining more faithful to a target model's LOO error than prior context attribution methods. This stark increase in performance makes computing context attributions for a given response $30\times$ faster than generating the response itself, empowering real-world applications that require computing attributions at scale. We release a user-friendly and efficient implementation of AttriBoT to enable efficient LLM interpretability as well as encourage future development of efficient context attribution methods.

Details

TMLR Journal 2025 Journal Article

ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization

  • Prateek Yadav
  • Leshem Choshen
  • Colin Raffel
  • Mohit Bansal

Parameter-efficient fine-tuning (PEFT) enables creation of specialized language models for diverse tasks, resulting in numerous expert modules. In many practical use cases, these expert PEFT modules are integrated into a single model that answers arbitrary queries by routing queries to different experts. However, only a few experts can be kept in GPU memory due to memory constraints. Consequently, expert modules are frequently loaded and offloaded between CPU/GPU memory or disk storage. This frequent swapping dramatically increases communication overhead, leading unacceptable latency and degrading user experience. The large size of modern PEFT modules further exacerbates this latency. For example, QLoRA experts for 65B LLaMA are 3.2GB, making swapping a major communication bottleneck, particularly in memory-constrained environments. To address these issues, we present ComPEFT (compressed PEFT), a novel method for compressing fine-tuning residuals (task vectors) of PEFT models. Reducing expert PEFT module size effectively addresses both memory and communication limitations, facilitating faster swapping and enabling a higher density of experts within a given memory footprint. ComPEFT employs sparsification and ternary quantization to reduce PEFT module size without any additional training while preserving or enhancing model performance. Extensive evaluation across T5, T0, and LLaMA-based models with 200M − 65B parameters, ComPEFT achieves compression ratios of 8x − 50x. Specifically, we show that ComPEFT improves with scale – stronger models exhibit higher compressibility and better performance. We show ComPEFT applied to LLaMA − 65B outperforms QLoRA by 4.16% on MMLU with a 26x storage size reduction. Additionally, compressed experts produced by ComPEFT maintain few-shot compositional generalization capabilities, facilitate efficient communication and computation, and exhibit enhanced performance when merged. Lastly, we provide an analysis of different method components, compare ComPEFT with other PEFT methods, and test its efficacy for compressing full finetuning residual.

PDF Details

NeurIPS Conference 2025 Conference Paper

Enhancing Training Data Attribution with Representational Optimization

  • Weiwei Sun
  • Haokun Liu
  • Nikhil Kandpal
  • Colin Raffel
  • Yiming Yang

Training data attribution (TDA) methods aim to measure how training data impacts a model's predictions. While gradient-based attribution methods, such as influence functions, offer theoretical grounding, their computational costs make them impractical for large-scale applications. Representation-based approaches are far more scalable, but typically rely on heuristic embeddings that are not optimized for attribution, limiting their fidelity. To address these challenges, we propose AirRep, a scalable, representation-based approach that closes this gap by learning task-specific and model-aligned representations optimized explicitly for TDA. AirRep introduces two key innovations: a trainable encoder tuned for attribution quality, and an attention-based pooling mechanism that enables accurate estimation of group-wise influence. We train AirRep using a ranking objective over automatically constructed training subsets labeled by their empirical effect on target predictions. Experiments on instruction-tuned LLMs demonstrate that AirRep achieves performance on par with state-of-the-art gradient-based approaches while being nearly two orders of magnitude more efficient at inference time. Further analysis highlights its robustness and generalization across tasks and models. Our code is available at https: //github. com/sunnweiwei/AirRep.

PDF Details

ICML Conference 2025 Conference Paper

Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator

  • Yu Xin Li
  • Felix Dangel
  • Derek Tam
  • Colin Raffel

The diagonal of a model’s Fisher Information Matrix (the "Fisher") has frequently been used as a way to measure parameter sensitivity. Typically, the Fisher is estimated by computing the squared gradient of the model’s outputs with respect to its parameters, averaged over a few hundred or thousand examples — a process which incurs nontrivial computational costs. At the same time, adaptive gradient methods like the ubiquitous Adam optimizer compute a moving average of the squared gradient over the course of training. This paper therefore explores whether an approximation of the Fisher can be obtained "for free" by recycling the squared gradient accumulator that has already been computed over the course of training. Through a comprehensive set of experiments covering five applications of the Fisher, we demonstrate that the "Squisher" ( Squ ared gradient accumulator as an approximation of the F isher ) consistently performs similarly to the Fisher while outperforming baseline methods. Additionally, we clarify the exact differences between the Squisher and the Fisher and provide empirical quantification of their respective impact.

Details

JMLR Journal 2025 Journal Article

Scaling Data-Constrained Language Models

  • Niklas Muennighoff
  • Alexander M. Rush
  • Boaz Barak
  • Teven Le Scao
  • Aleksandra Piktus
  • Nouamane Tazi
  • Sampo Pyysalo
  • Thomas Wolf

The current trend of scaling language models involves increasing both parameter count and training data set size. Extrapolating this trend suggests that training data set size may soon be limited by the amount of text data available on the internet. Motivated by this limit, we investigate scaling language models in data-constrained regimes. Specifically, we run a large set of experiments varying the extent of data repetition and compute budget, ranging up to 900 billion training tokens and 9 billion parameter models. We find that with constrained data for a fixed compute budget, training with up to 4 epochs of repeated data yields negligible changes to loss compared to having unique data. However, with more repetition, the value of adding compute eventually decays to zero. We propose and empirically validate a scaling law for compute optimality that accounts for the decreasing value of repeated tokens and excess parameters. Finally, we experiment with approaches mitigating data scarcity, including augmenting the training data set with code data or removing commonly used filters. Models and data sets from our 400 training runs are freely available at https://github.com/huggingface/datablations. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2025. ( edit, beta )

PDF Details

ICML Conference 2025 Conference Paper

The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions

  • Gül Sena Altintas
  • Devin Kwok
  • Colin Raffel
  • David Rolnick

Neural network training is inherently sensitive to initialization and the randomness induced by stochastic gradient descent. However, it is unclear to what extent such effects lead to meaningfully different networks, either in terms of the models’ weights or the underlying functions that were learned. In this work, we show that during the initial "chaotic" phase of training, even extremely small perturbations reliably causes otherwise identical training trajectories to diverge-an effect that diminishes rapidly over training time. We quantify this divergence through (i) $L^2$ distance between parameters, (ii) the loss barrier when interpolating between networks, (iii) $L^2$ and barrier between parameters after permutation alignment, and (iv) representational similarity between intermediate activations; revealing how perturbations across different hyperparameter or fine-tuning settings drive training trajectories toward distinct loss minima. Our findings provide insights into neural network training stability, with practical implications for fine-tuning, model merging, and diversity of model ensembles.

Details

NeurIPS Conference 2025 Conference Paper

The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text

  • Nikhil Kandpal
  • Brian Lester
  • Colin Raffel
  • Sebastian Majstorovic
  • Stella Biderman
  • Baber Abbasi
  • Luca Soldaini
  • Enrico Shippole

Large language models (LLMs) are typically trained on enormous quantities of unlicensed text, a practice that has led to scrutiny due to possible intellectual property infringement and ethical concerns. Training LLMs on openly licensed text presents a first step towards addressing these issues, but prior data collection efforts have yielded datasets too small or low-quality to produce performant LLMs. To address this gap, we collect, curate, and release the Common Pile v0. 1, an eight terabyte collection of openly licensed text designed for LLM pretraining. The Common Pile comprises content from 30 sources that span diverse domains including research papers, code, books, encyclopedias, educational materials, audio transcripts, and more. Crucially, we validate our efforts by training two 7 billion parameter LLMs on text from the Common Pile: Comma v0. 1-1T and Comma v0. 1-2T, trained on 1 and 2 trillion tokens respectively. Both models attain competitive performance to LLMs trained on unlicensed text with similar computational budgets, such as Llama 1 and 2 7B. In addition to releasing the Common Pile v0. 1 itself, we also release the code used in its creation as well as the training mixture and checkpoints for the Comma v0. 1 models.

PDF Details

TMLR Journal 2024 Journal Article

A Survey on Data Selection for Language Models

  • Alon Albalak
  • Yanai Elazar
  • Sang Michael Xie
  • Shayne Longpre
  • Nathan Lambert
  • Xinyi Wang
  • Niklas Muennighoff
  • Bairu Hou

A major factor in the recent success of large language models is the use of enormous and ever-growing text datasets for unsupervised pre-training. However, naively training a model on all available data may not be optimal (or feasible), as the quality of available text data can vary. Filtering out data can also decrease the carbon footprint and financial costs of training models by reducing the amount of training required. Data selection methods aim to determine which candidate data points to include in the training dataset and how to appropriately sample from the selected data points. The promise of improved data selection methods has caused the volume of research in the area to rapidly expand. However, because deep learning is mostly driven by empirical evidence and experimentation on large-scale data is expensive, few organizations have the resources for extensive data selection research. Consequently, knowledge of effective data selection practices has become concentrated within a few organizations, many of which do not openly share their findings and methodologies. To narrow this gap in knowledge, we present a comprehensive review of existing literature on data selection methods and related research areas, providing a taxonomy of existing approaches. By describing the current landscape of research, this work aims to accelerate progress in data selection by establishing an entry point for new and established researchers. Additionally, throughout this review we draw attention to noticeable holes in the literature and conclude the paper by proposing promising avenues for future research.

PDF Details

ICML Conference 2024 Conference Paper

Learning to Route Among Specialized Experts for Zero-Shot Generalization

  • Mohammed Muqeeth
  • Haokun Liu
  • Yufan Liu
  • Colin Raffel

Recently, there has been a widespread proliferation of "expert" language models that are specialized to a specific task or domain through parameter-efficient fine-tuning. How can we recycle large collections of expert language models to improve zero-shot generalization to unseen tasks? In this work, we propose $\textbf{P}$ost-$\textbf{H}$oc $\textbf{A}$daptive $\textbf{T}$okenwise $\textbf{G}$ating $\textbf{O}$ver an $\textbf{O}$cean of $\textbf{S}$pecialized $\textbf{E}$xperts ( PHATGOOSE ), which learns to route among specialized modules that were produced through parameter-efficient fine-tuning. Unlike past methods that learn to route among specialized models, PHATGOOSE explores the possibility that zero-shot generalization will be improved if different experts can be adaptively chosen for each token and at each layer in the model. Crucially, our method is post-hoc - it does not require simultaneous access to the datasets used to create the specialized models and only requires a modest amount of additional compute after each expert model is trained. In experiments covering a range of specialized model collections and zero-shot generalization benchmarks, we find that PHATGOOSE outperforms past methods for post-hoc routing and, in some cases, outperforms explicit multitask training (which requires simultaneous data access). To better understand the routing strategy learned by PHATGOOSE, we perform qualitative experiments to validate that PHATGOOSE’s performance stems from its ability to make adaptive per-token and per-module expert choices.

Details

TMLR Journal 2024 Journal Article

Merging by Matching Models in Task Parameter Subspaces

  • Derek Tam
  • Mohit Bansal
  • Colin Raffel

Model merging aims to cheaply combine individual task-specific models into a single multitask model. In this work, we view past merging methods as leveraging different notions of a ''task parameter subspace'' in which models are matched before being merged. We connect the task parameter subspace of a given model to its loss landscape and formalize how this approach to model merging can be seen as solving a linear system of equations. While past work has generally been limited to linear systems that have a closed-form solution, we consider using the conjugate gradient method to find a solution. We show that using the conjugate gradient method can outperform closed-form solutions, enables merging via linear systems that are otherwise intractable to solve, and flexibly allows choosing from a wide variety of initializations and estimates for the ''task parameter subspace''. We ultimately demonstrate that our merging framework called ''Matching Models in their Task Parameter Subspace'' (MATS) achieves state-of-the-art results in multitask and intermediate-task model merging. We release all of the code and checkpoints used in our work.

PDF Details

TMLR Journal 2024 Journal Article

Soft Merging of Experts with Adaptive Routing

  • Mohammed Muqeeth
  • Haokun Liu
  • Colin Raffel

Neural networks that learn to route their inputs through different "expert" subnetworks provide a form of modularity that standard dense models lack. Despite their possible benefits, modular models with learned routing often underperform their parameter-matched dense counterparts as well as models that use non-learned heuristic routing strategies. In this paper, we hypothesize that these shortcomings stem from the gradient estimation techniques used to train modular models that use non-differentiable discrete routing decisions. To address this issue, we introduce $\textbf{S}$oft $\textbf{M}$erging of $\textbf{E}$xperts with $\textbf{A}$daptive $\textbf{R}$outing (SMEAR), which avoids discrete routing by using a single "merged" expert constructed via a weighted average of all of the experts' parameters. By routing activations through a single merged expert, SMEAR does not incur a significant increase in computational costs and enables standard gradient-based training. We empirically validate that models using SMEAR outperform models that route based on metadata or learn routing through gradient estimation. Furthermore, we provide qualitative analysis demonstrating that the experts learned via SMEAR exhibit a significant amount of specialization.

PDF Details

NeurIPS Conference 2024 Conference Paper

The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale

  • Guilherme Penedo
  • Hynek Kydlíček
  • Loubna B. allal
  • Anton Lozhkov
  • Margaret Mitchell
  • Colin Raffel
  • Leandro Von Werra
  • Thomas Wolf

The performance of a large language model (LLM) depends heavily on the quality and size of its pretraining dataset. However, the pretraining datasets for state-of-the-art open LLMs like Llama 3 and Mixtral are not publicly available and very little is known about how they were created. In this work, we introduce FineWeb, a 15-trillion token dataset derived from 96 Common Crawl snapshots that produces better-performing LLMs than other open pretraining datasets. To advance the understanding of how best to curate high-quality pretraining datasets, we carefully document and ablate all of the design choices used in FineWeb, including in-depth investigations of deduplication and filtering strategies. In addition, we introduce FineWeb-Edu, a 1. 3-trillion token collection of educational text filtered from FineWeb. LLMs pretrained on FineWeb-Edu exhibit dramatically better performance on knowledge- and reasoning-intensive benchmarks like MMLU and ARC. Along with our datasets, we publicly release our data curation codebase and all of the models trained during our ablation experiments.

PDF Details DOI

TMLR Journal 2023 Journal Article

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

  • Aarohi Srivastava
  • Abhinav Rastogi
  • Abhishek Rao
  • Abu Awal Md Shoeb
  • Abubakar Abid
  • Adam Fisch
  • Adam R. Brown
  • Adam Santoro

Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabilities are as yet poorly characterized. In order to inform future research, prepare for disruptive new model capabilities, and ameliorate socially harmful effects, it is vital that we understand the present and near-future capabilities and limitations of language models. To address this challenge, we introduce the Beyond the Imitation Game benchmark (BIG- bench). BIG-bench currently consists of 204 tasks, contributed by 450 authors across 132 institutions. Task topics are diverse, drawing problems from linguistics, childhood develop- ment, math, common-sense reasoning, biology, physics, social bias, software development, and beyond. BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models. We evaluate the behavior of OpenAI's GPT models, Google- internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters. In addition, a team of human expert raters performed all tasks in order to provide a strong baseline. Findings include: model performance and calibration both improve with scale, but are poor in absolute terms (and when compared with rater performance); performance is remarkably similar across model classes, though with benefits from sparsity; tasks that improve gradually and predictably commonly involve a large knowledge or memorization component, whereas tasks that exhibit "breakthrough" behavior at a critical scale often involve multiple steps or components, or brittle metrics; social bias typically increases with scale in settings with ambiguous context, but this can be improved with prompting.

PDF Details

ICLR Conference 2023 Conference Paper

Bidirectional Language Models Are Also Few-shot Learners

  • Ajay Patel
  • Bryan Li
  • Mohammad Sadegh Rasooli
  • Noah Constant
  • Colin Raffel
  • Chris Callison-Burch

Large language models such as GPT-3 (Brown et al., 2020) can perform arbitrary tasks without undergoing fine-tuning after being prompted with only a few labeled examples. An arbitrary task can be reformulated as a natural language prompt, and a language model can be asked to generate the completion, indirectly performing the task in a paradigm known as prompt-based learning. To date, emergent prompt-based learning capabilities have mainly been demonstrated for unidirectional language models. However, bidirectional language models pre-trained on denoising objectives such as masked language modeling produce stronger learned representations for transfer learning. This motivates the possibility of prompting bidirectional models, but their pre-training objectives have made them largely incompatible with the existing prompting paradigm. We present SAP (Sequential Autoregressive Prompting), a technique that enables the prompting of bidirectional models. Utilizing the machine translation task as a case study, we prompt the bidirectional mT5 model (Xue et al., 2021) with SAP and demonstrate its few-shot and zero-shot translations outperform the few-shot translations of unidirectional models like GPT-3 and XGLM (Lin et al., 2021), despite mT5's approximately 50% fewer parameters. We further show SAP is effective on question answering and summarization. For the first time, our results demonstrate prompt-based learning is an emergent property of a broader class of language models, rather than only unidirectional models.

Details

ICML Conference 2023 Conference Paper

Git-Theta: A Git Extension for Collaborative Development of Machine Learning Models

  • Nikhil Kandpal
  • Brian Lester
  • Mohammed Muqeeth
  • Anisha Mascarenhas
  • Monty Evans
  • Vishal Baskaran
  • Tenghao Huang
  • Haokun Liu

Currently, most machine learning models are trained by centralized teams and are rarely updated. In contrast, open-source software development involves the iterative development of a shared artifact through distributed collaboration using a version control system. In the interest of enabling collaborative and continual improvement of machine learning models (Raffel, 2023), we introduce Git-Theta, a version control system for machine learning models. Git-Theta is an extension to Git, the most widely used version control software, that allows fine-grained tracking of changes to model parameters alongside code and other artifacts. Unlike existing version control systems that treat a model checkpoint as a blob of data, Git-Theta leverages the structure of checkpoints to support communication-efficient updates, automatic model merges, and meaningful reporting about the difference between two versions of a model. In addition, Git-Theta includes a plug-in system that enables users to easily add support for new functionality. In this paper, we introduce Git-Theta’s design and features and include an example use-case of Git-Theta where a pre-trained model is continually adapted and modified. We publicly release Git-Theta in hopes of kickstarting a new era of collaborative model development. https: //github. com/r-three/git-theta/

Details

ICML Conference 2023 Conference Paper

Large Language Models Struggle to Learn Long-Tail Knowledge

  • Nikhil Kandpal
  • Haikang Deng
  • Adam Roberts
  • Eric Wallace
  • Colin Raffel

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, while certain pieces of information are ubiquitous on the web, others appear extremely rarely. In this paper, we study the relationship between the knowledge memorized by large language models and the information in pre-training datasets scraped from the web. In particular, we show that a language model’s ability to answer a fact-based question relates to how many documents associated with that question were seen during pre-training. We identify these relevant documents by entity linking pre-training datasets and counting documents that contain the same entities as a given question-answer pair. Our results demonstrate strong correlational and causal relationships between accuracy and relevant document count for numerous question answering datasets (e. g. , TriviaQA), pre-training corpora (e. g. , ROOTS), and model sizes (e. g. , 176B parameters). Moreover, while larger models are better at learning long-tail knowledge, we estimate that today’s models must be scaled by many orders of magnitude to reach competitive QA performance on questions with little support in the pre-training data. Finally, we show that retrieval-augmentation can reduce the dependence on relevant pre-training information, presenting a promising approach for capturing the long-tail.

Details

JMLR Journal 2023 Journal Article

Scaling Up Models and Data with t5x and seqio

  • Adam Roberts
  • Hyung Won Chung
  • Gaurav Mishra
  • Anselm Levskaya
  • James Bradbury
  • Daniel Andor
  • Sharan Narang
  • Brian Lester

Scaling up training datasets and model parameters have benefited neural network-based language models, but also present challenges like distributed compute, input data bottlenecks and reproducibility of results. We introduce two simple and scalable software libraries that simplify these issues: t5x enables training large language models at scale, while seqio enables reproducible input and evaluation pipelines. These open-source libraries have been used to train models with hundreds of billions of parameters on multi-terabyte datasets. Configurations and instructions for T5-like and GPT-like models are also provided. The libraries can be found at https://github.com/google-research/t5x and https://github.com/google/seqio. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2023. ( edit, beta )

PDF Details

ICML Conference 2022 Conference Paper

Deduplicating Training Data Mitigates Privacy Risks in Language Models

  • Nikhil Kandpal
  • Eric Wallace
  • Colin Raffel

Past work has shown that large language models are susceptible to privacy attacks, where adversaries generate sequences from a trained model and detect which sequences are memorized from the training set. In this work, we show that the success of these attacks is largely due to duplication in commonly used web-scraped training sets. We first show that the rate at which language models regenerate training sequences is superlinearly related to a sequence’s count in the training set. For instance, a sequence that is present 10 times in the training data is on average generated 1000x more often than a sequence that is present only once. We next show that existing methods for detecting memorized sequences have near-chance accuracy on non-duplicated training sequences. Finally, we find that after applying methods to deduplicate training data, language models are considerably more secure against these types of privacy attacks. Taken together, our results motivate an increased focus on deduplication in privacy-sensitive applications and a reevaluation of the practicality of existing privacy attacks.

Details

TMLR Journal 2022 Journal Article

Emergent Abilities of Large Language Models

  • Jason Wei
  • Yi Tay
  • Rishi Bommasani
  • Colin Raffel
  • Barret Zoph
  • Sebastian Borgeaud
  • Dani Yogatama
  • Maarten Bosma

Scaling up language models has been shown to predictably improve performance and sample efficiency on a wide range of downstream tasks. This paper instead discusses an unpredictable phenomenon that we refer to as emergent abilities of large language models. We consider an ability to be emergent if it is not present in smaller models but is present in larger models. Thus, emergent abilities cannot be predicted simply by extrapolating the performance of smaller models. The existence of such emergence raises the question of whether additional scaling could potentially further expand the range of capabilities of language models.

PDF Details

ICLR Conference 2022 Conference Paper

Multitask Prompted Training Enables Zero-Shot Task Generalization

  • Victor Sanh
  • Albert Webson
  • Colin Raffel
  • Stephen H. Bach
  • Lintang Sutawika
  • Zaid Alyafeai
  • Antoine Chaffin
  • Arnaud Stiegler

Large language models have recently been shown to attain reasonable zero-shot generalization on a diverse set of tasks (Brown et al., 2020). It has been hypothesized that this is a consequence of implicit multitask learning in language models’ pretraining (Radford et al., 2019). Can zero-shot generalization instead be directly induced by explicit multitask learning? To test this question at scale, we develop a system for easily mapping any natural language tasks into a human-readable prompted form. We convert a large set of supervised datasets, each with multiple prompts with diverse wording. These prompted datasets allow for benchmarking the ability of a model to perform completely unseen tasks specified in natural language. We fine-tune a pretrained encoder-decoder model (Raffel et al., 2020; Lester et al., 2021) on this multitask mixture covering a wide variety of tasks. The model attains strong zero-shot performance on several datasets, often outperforming models 16× its size. Further, our model attains strong performance on a subset of tasks from the BIG-Bench benchmark, outperforming models 6× its size. All trained models are available at https://github.com/bigscience-workshop/t-zero, and all prompts are available at https://github.com/bigscience-workshop/promptsource.

Details

ICML Conference 2022 Conference Paper

What Language Model Architecture and Pretraining Objective Works Best for Zero-Shot Generalization?

  • Thomas Wang
  • Adam Roberts
  • Daniel Hesslow
  • Teven Le Scao
  • Hyung Won Chung
  • Iz Beltagy
  • Julien Launay
  • Colin Raffel

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 trained on. However, the architectures and pretraining objectives used across state-of-the-art models differ significantly, and there has been limited systematic comparison of these factors. In this work, we present a large-scale evaluation of modeling choices and their impact on zero-shot generalization. In particular, we focus on text-to-text models and experiment with three model architectures (causal/non-causal decoder-only and encoder-decoder), trained with two different pretraining objectives (autoregressive and masked language modeling), and evaluated with and without multitask prompted finetuning. We train models with over 5 billion parameters for more than 168 billion tokens, thereby increasing the likelihood that our conclusions will transfer to even larger scales. Our experiments show that causal decoder-only models trained on an autoregressive language modeling objective exhibit the strongest zero-shot generalization after purely self-supervised pretraining. However, models with non-causal visibility on their input trained with a masked language modeling objective followed by multitask finetuning perform the best among our experiments. We therefore consider the adaptation of pretrained models across architectures and objectives. Code and checkpoints are available at https: //github. com/bigscience- workshop/architecture-objective.

Details

ICLR Conference 2021 Conference Paper

Robust and Generalizable Visual Representation Learning via Random Convolutions

  • Zhenlin Xu
  • Deyi Liu
  • Junlin Yang
  • Colin Raffel
  • Marc Niethammer

While successful for various computer vision tasks, deep neural networks have shown to be vulnerable to texture style shifts and small perturbations to which humans are robust. In this work, we show that the robustness of neural networks can be greatly improved through the use of random convolutions as data augmentation. Random convolutions are approximately shape-preserving and may distort local textures. Intuitively, randomized convolutions create an infinite number of new domains with similar global shapes but random local texture. Therefore, we explore using outputs of multi-scale random convolutions as new images or mixing them with the original images during training. When applying a network trained with our approach to unseen domains, our method consistently improves the performance on domain generalization benchmarks and is scalable to ImageNet. In particular, in the challenging scenario of generalizing to the sketch domain in PACS and to ImageNet-Sketch, our method outperforms state-of-art methods by a large margin. More interestingly, our method can benefit downstream tasks by providing a more robust pretrained visual representation.

Details

ICLR Conference 2020 Conference Paper

Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructions

  • Yao Qin 0001
  • Nicholas Frosst
  • Sara Sabour
  • Colin Raffel
  • Garrison W. Cottrell
  • Geoffrey E. Hinton

Adversarial examples raise questions about whether neural network models are sensitive to the same visual features as humans. In this paper, we first detect adversarial examples or otherwise corrupted images based on a class-conditional reconstruction of the input. To specifically attack our detection mechanism, we propose the Reconstructive Attack which seeks both to cause a misclassification and a low reconstruction error. This reconstructive attack produces undetected adversarial examples but with much smaller success rate. Among all these attacks, we find that CapsNets always perform better than convolutional networks. Then, we diagnose the adversarial examples for CapsNets and find that the success of the reconstructive attack is highly related to the visual similarity between the source and target class. Additionally, the resulting perturbations can cause the input image to appear visually more like the target class and hence become non-adversarial. This suggests that CapsNets use features that are more aligned with human perception and have the potential to address the central issue raised by adversarial examples.

Details

JMLR Journal 2020 Journal Article

Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

  • Colin Raffel
  • Noam Shazeer
  • Adam Roberts
  • Katherine Lee
  • Sharan Narang
  • Michael Matena
  • Yanqi Zhou
  • Wei Li

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 processing (NLP). The effectiveness of transfer learning has given rise to a diversity of approaches, methodology, and practice. In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts all text-based language problems into a text-to-text format. Our systematic study compares pre-training objectives, architectures, unlabeled data sets, transfer approaches, and other factors on dozens of language understanding tasks. By combining the insights from our exploration with scale and our new “Colossal Clean Crawled Corpus”, we achieve state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more. To facilitate future work on transfer learning for NLP, we release our data set, pre-trained models, and code. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2020. ( edit, beta )

PDF Details

ICLR Conference 2020 Conference Paper

ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation Anchoring

  • David Berthelot
  • Nicholas Carlini
  • Ekin Dogus Cubuk
  • Alexey Kurakin
  • Kihyuk Sohn
  • Han Zhang 0010
  • Colin Raffel

We improve the recently-proposed ``MixMatch semi-supervised learning algorithm by introducing two new techniques: distribution alignment and augmentation anchoring. - Distribution alignment encourages the marginal distribution of predictions on unlabeled data to be close to the marginal distribution of ground-truth labels. - Augmentation anchoring} feeds multiple strongly augmented versions of an input into the model and encourages each output to be close to the prediction for a weakly-augmented version of the same input. To produce strong augmentations, we propose a variant of AutoAugment which learns the augmentation policy while the model is being trained. Our new algorithm, dubbed ReMixMatch, is significantly more data-efficient than prior work, requiring between 5 times and 16 times less data to reach the same accuracy. For example, on CIFAR-10 with 250 labeled examples we reach 93.73% accuracy (compared to MixMatch's accuracy of 93.58% with 4000 examples) and a median accuracy of 84.92% with just four labels per class.

Details

ICML Conference 2019 Conference Paper

Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition

  • Yao Qin 0001
  • Nicholas Carlini
  • Garrison W. Cottrell
  • Ian J. Goodfellow
  • Colin Raffel

Adversarial examples are inputs to machine learning models designed by an adversary to cause an incorrect output. So far, adversarial examples have been studied most extensively in the image domain. In this domain, adversarial examples can be constructed by imperceptibly modifying images to cause misclassification, and are practical in the physical world. In contrast, current targeted adversarial examples on speech recognition systems have neither of these properties: humans can easily identify the adversarial perturbations, and they are not effective when played over-the-air. This paper makes progress on both of these fronts. First, we develop effectively imperceptible audio adversarial examples (verified through a human study) by leveraging the psychoacoustic principle of auditory masking, while retaining 100% targeted success rate on arbitrary full-sentence targets. Then, we make progress towards physical-world audio adversarial examples by constructing perturbations which remain effective even after applying highly-realistic simulated environmental distortions.

Details

NeurIPS Conference 2019 Conference Paper

MixMatch: A Holistic Approach to Semi-Supervised Learning

  • David Berthelot
  • Nicholas Carlini
  • Ian Goodfellow
  • Nicolas Papernot
  • Avital Oliver
  • Colin Raffel

Semi-supervised learning has proven to be a powerful paradigm for leveraging unlabeled data to mitigate the reliance on large labeled datasets. In this work, we unify the current dominant approaches for semi-supervised learning to produce a new algorithm, MixMatch, that guesses low-entropy labels for data-augmented unlabeled examples and mixes labeled and unlabeled data using MixUp. MixMatch obtains state-of-the-art results by a large margin across many datasets and labeled data amounts. For example, on CIFAR-10 with 250 labels, we reduce error rate by a factor of 4 (from 38% to 11%) and by a factor of 2 on STL-10. We also demonstrate how MixMatch can help achieve a dramatically better accuracy-privacy trade-off for differential privacy. Finally, we perform an ablation study to tease apart which components of MixMatch are most important for its success. Code is attached.

PDF Details

ICML Conference 2018 Conference Paper

A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music

  • Adam Roberts
  • Jesse H. Engel
  • Colin Raffel
  • Curtis Hawthorne
  • Douglas Eck

The Variational Autoencoder (VAE) has proven to be an effective model for producing semantically meaningful latent representations for natural data. However, it has thus far seen limited application to sequential data, and, as we demonstrate, existing recurrent VAE models have difficulty modeling sequences with long-term structure. To address this issue, we propose the use of a hierarchical decoder, which first outputs embeddings for subsequences of the input and then uses these embeddings to generate each subsequence independently. This structure encourages the model to utilize its latent code, thereby avoiding the "posterior collapse" problem which remains an issue for recurrent VAEs. We apply this architecture to modeling sequences of musical notes and find that it exhibits dramatically better sampling, interpolation, and reconstruction performance than a "flat" baseline model. An implementation of our "MusicVAE" is available online at https: //goo. gl/magenta/musicvae-code.

Details

ICML Conference 2018 Conference Paper

Is Generator Conditioning Causally Related to GAN Performance?

  • Augustus Odena
  • Jacob Buckman
  • Catherine Olsson
  • Tom B. Brown
  • Christopher Olah
  • Colin Raffel
  • Ian J. Goodfellow

Recent work suggests that controlling the entire distribution of Jacobian singular values is an important design consideration in deep learning. Motivated by this, we study the distribution of singular values of the Jacobian of the generator in Generative Adversarial Networks. We find that this Jacobian generally becomes ill-conditioned at the beginning of training. Moreover, we find that the average (across the latent space) conditioning of the generator is highly predictive of two other ad-hoc metrics for measuring the “quality” of trained GANs: the Inception Score and the Frechet Inception Distance. We then test the hypothesis that this relationship is causal by proposing a “regularization” technique (called Jacobian Clamping) that softly penalizes the condition number of the generator Jacobian. Jacobian Clamping improves the mean score for nearly all datasets on which we tested it. It also greatly reduces inter-run variance of the aforementioned scores, addressing (at least partially) one of the main criticisms of GANs.

Details

NeurIPS Conference 2018 Conference Paper

Realistic Evaluation of Deep Semi-Supervised Learning Algorithms

  • Avital Oliver
  • Augustus Odena
  • Colin Raffel
  • Ekin Dogus Cubuk
  • Ian Goodfellow

Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data when labels are limited or expensive to obtain. SSL algorithms based on deep neural networks have recently proven successful on standard benchmark tasks. However, we argue that these benchmarks fail to address many issues that SSL algorithms would face in real-world applications. After creating a unified reimplementation of various widely-used SSL techniques, we test them in a suite of experiments designed to address these issues. We find that the performance of simple baselines which do not use unlabeled data is often underreported, SSL methods differ in sensitivity to the amount of labeled and unlabeled data, and performance can degrade substantially when the unlabeled dataset contains out-of-distribution examples. To help guide SSL research towards real-world applicability, we make our unified reimplemention and evaluation platform publicly available.

PDF Details

ICML Conference 2017 Conference Paper

Online and Linear-Time Attention by Enforcing Monotonic Alignments

  • Colin Raffel
  • Minh-Thang Luong
  • Peter J. Liu
  • Ron J. Weiss
  • Douglas Eck

Recurrent neural network models with an attention mechanism have proven to be extremely effective on a wide variety of sequence-to-sequence problems. However, the fact that soft attention mechanisms perform a pass over the entire input sequence when producing each element in the output sequence precludes their use in online settings and results in a quadratic time complexity. Based on the insight that the alignment between input and output sequence elements is monotonic in many problems of interest, we propose an end-to-end differentiable method for learning monotonic alignments which, at test time, enables computing attention online and in linear time. We validate our approach on sentence summarization, machine translation, and online speech recognition problems and achieve results competitive with existing sequence-to-sequence models.

Details

AAAI Conference 2016 Conference Paper

Poker-CNN: A Pattern Learning Strategy for Making Draws and Bets in Poker Games Using Convolutional Networks

  • Nikolai Yakovenko
  • LiangLiang Cao
  • Colin Raffel
  • James Fan

Poker is a family of card games that includes many variations. We hypothesize that most poker games can be solved as a pattern matching problem, and propose creating a strong poker playing system based on a unified poker representation. Our poker player learns through iterative self-play, and improves its understanding of the game by training on the results of its previous actions without sophisticated domain knowledge. We evaluate our system on three poker games: single player video poker, two-player Limit Texas Hold’em, and finally two-player 2-7 triple draw poker. We show that our model can quickly learn patterns in these very different poker games while it improves from zero knowledge to a competitive player against human experts. The contributions of this paper include: (1) a novel representation for poker games, extendable to different poker variations, (2) a Convolutional Neural Network (CNN) based learning model that can effectively learn the patterns in three different games, and (3) a self-trained system that significantly beats the heuristic-based program on which it is trained, and our system is competitive against human expert players.

PDF Details
v2026.09.13