Author name cluster

Douwe Kiela

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.

23 papers

2 author rows

ICLR Conference 2025 Conference Paper

Generative Representational Instruction Tuning

Niklas Muennighoff
Hongjin Su
Liang Wang 0046
Nan Yang 0002
Furu Wei
Tao Yu 0009
Amanpreet Singh
Douwe Kiela

All text-based language problems can be reduced to either generation or embedding. Current models only perform well at one or the other. We introduce generative representational instruction tuning (GRIT) whereby a large language model is trained to handle both generative and embedding tasks by distinguishing between them through instructions. Compared to other open models, our resulting GritLM-7B is among the top models on the Massive Text Embedding Benchmark (MTEB) and outperforms various models up to its size on a range of generative tasks. By scaling up further, GritLM-8x7B achieves even stronger generative performance while still being among the best embedding models. Notably, we find that GRIT matches training on only generative or embedding data, thus we can unify both at no performance loss. Among other benefits, the unification via GRIT speeds up Retrieval-Augmented Generation (RAG) by > 60% for long documents, by no longer requiring separate retrieval and generation models. Models, code, etc. are freely available at https://github.com/ContextualAI/gritlm.

Details

ICML Conference 2025 Conference Paper

Great Models Think Alike and this Undermines AI Oversight

Shashwat Goel
Joschka Strüber
Ilze Amanda Auzina
Karuna K. Chandra
Ponnurangam Kumaraguru
Douwe Kiela
Ameya Prabhu
Matthias Bethge

As Language Model (LM) capabilities advance, evaluating and supervising them at scale is getting harder for humans. There is hope that other language models can automate both these tasks, which we refer to as AI Oversight. We study how model similarity affects both aspects of AI oversight by proposing Chance Adjusted Probabilistic Agreement (CAPA) –a metric for LM similarity based on overlap in model mistakes. Using CAPA, we first show that LLM-as-a-judge scores favor models similar to the judge, generalizing recent self-preference results. Then, we study training on LM annotations, and find complementary knowledge between the weak supervisor and strong student model plays a crucial role in gains from weak-to-strong generalization. As model capabilities increase, it becomes harder to find their mistakes, and we might defer more to AI oversight. However, we observe a concerning trend–model mistakes are becoming more similar with increasing capabilities, pointing to risks from correlated failures. Our work underscores the importance of reporting and correcting for model similarity, especially in the emerging paradigm of AI oversight.

Details

ICLR Conference 2025 Conference Paper

OLMoE: Open Mixture-of-Experts Language Models

Niklas Muennighoff
Luca Soldaini
Dirk Groeneveld
Kyle Lo
Jacob Morrison
Sewon Min
Weijia Shi
Evan Pete Walsh

We introduce OLMoE, a fully open, state-of-the-art language model leveraging sparse Mixture-of-Experts (MoE). OLMoE-1B-7B has 7 billion (B) parameters but uses only 1B per input token. We pretrain it on 5 trillion tokens and further adapt it to create OLMoE-1B-7B-Instruct. Our models outperform all available models with similar active parameters, even surpassing larger ones like Llama2-13B-Chat and DeepSeekMoE-16B. We present novel findings on MoE training, define and analyze new routing properties showing high specialization in our model, and open-source all our work: model weights, training data, code, and logs.

Details

AAAI Conference 2024 Conference Paper

Leveraging Diffusion Perturbations for Measuring Fairness in Computer Vision

Nicholas Lui
Bryan Chia
William Berrios
Candace Ross
Douwe Kiela

Computer vision models have been known to encode harmful biases, leading to the potentially unfair treatment of historically marginalized groups, such as people of color. However, there remains a lack of datasets balanced along demographic traits that can be used to evaluate the downstream fairness of these models. In this work, we demonstrate that diffusion models can be leveraged to create such a dataset. We first use a diffusion model to generate a large set of images depicting various occupations. Subsequently, each image is edited using inpainting to generate multiple variants, where each variant refers to a different perceived race. Using this dataset, we benchmark several vision-language models on a multi-class occupation classification task. We find that images generated with non-Caucasian labels have a significantly higher occupation misclassification rate than images generated with Caucasian labels, and that several misclassifications are suggestive of racial biases. We measure a model’s downstream fairness by computing the standard deviation in the probability of predicting the true occupation label across the different identity groups. Using this fairness metric, we find significant disparities between the evaluated vision-and-language models. We hope that our work demonstrates the potential value of diffusion methods for fairness evaluations.

PDF Details DOI

ICML Conference 2024 Conference Paper

Model Alignment as Prospect Theoretic Optimization

Kawin Ethayarajh
Winnie Xu
Niklas Muennighoff
Dan Jurafsky
Douwe Kiela

Kahneman & Tversky’s $\textit{prospect theory}$ tells us that humans perceive random variables in a biased but well-defined manner (1992); for example, humans are famously loss-averse. We show that objectives for aligning LLMs with human feedback implicitly incorporate many of these biases—the success of these objectives (e. g. , DPO) over cross-entropy minimization can partly be ascribed to them belonging to a family of loss functions that we call $\textit{human-aware losses}$ (HALOs). However, the utility functions these methods attribute to humans still differ from those in the prospect theory literature. Using a Kahneman-Tversky model of human utility, we propose a HALO that directly maximizes the utility of generations instead of maximizing the log-likelihood of preferences, as current methods do. We call this approach KTO, and it matches or exceeds the performance of preference-based methods at scales from 1B to 30B, despite only learning from a binary signal of whether an output is desirable. More broadly, our work suggests that there is no one HALO that is universally superior; the best loss depends on the inductive biases most appropriate for a given setting, an oft-overlooked consideration.

Details

NeurIPS Conference 2023 Conference Paper

DataPerf: Benchmarks for Data-Centric AI Development

Mark Mazumder
Colby Banbury
Xiaozhe Yao
Bojan Karlaš
William Gaviria Rojas
Sudnya Diamos
Greg Diamos
Lynn He

Machine learning research has long focused on models rather than datasets, and prominent datasets are used for common ML tasks without regard to the breadth, difficulty, and faithfulness of the underlying problems. Neglecting the fundamental importance of data has given rise to inaccuracy, bias, and fragility in real-world applications, and research is hindered by saturation across existing dataset benchmarks. In response, we present DataPerf, a community-led benchmark suite for evaluating ML datasets and data-centric algorithms. We aim to foster innovation in data-centric AI through competition, comparability, and reproducibility. We enable the ML community to iterate on datasets, instead of just architectures, and we provide an open, online platform with multiple rounds of challenges to support this iterative development. The first iteration of DataPerf contains five benchmarks covering a wide spectrum of data-centric techniques, tasks, and modalities in vision, speech, acquisition, debugging, and diffusion prompting, and we support hosting new contributed benchmarks from the community. The benchmarks, online evaluation platform, and baseline implementations are open source, and the MLCommons Association will maintain DataPerf to ensure long-term benefits to academia and industry.

PDF Details

NeurIPS Conference 2023 Conference Paper

OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents

Hugo Laurençon
Lucile Saulnier
Leo Tronchon
Stas Bekman
Amanpreet Singh
Anton Lozhkov
Thomas Wang
Siddharth Karamcheti

Large multimodal models trained on natural documents, which interleave images and text, outperform models trained on image-text pairs on various multimodal benchmarks. However, the datasets used to train these models have not been released, and the collection process has not been fully specified. We introduce the OBELICS dataset, an open web-scale filtered dataset of interleaved image-text documents comprising 141 million web pages extracted from Common Crawl, 353 million associated images, and 115 billion text tokens. We describe the dataset creation process, present comprehensive filtering rules, and provide an analysis of the dataset's content. To show the viability of OBELICS, we train on the dataset vision and language models of 9 and 80 billion parameters, IDEFICS-9B and IDEFICS, and obtain competitive performance on different multimodal benchmarks. We release our dataset, models and code.

PDF Details

ICLR Conference 2021 Conference Paper

Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval

Wenhan Xiong
Xiang Lorraine Li
Srini Iyer 0001
Jingfei Du
Patrick Lewis 0001
William Yang Wang
Yashar Mehdad
Wen-tau Yih

We propose a simple and efficient multi-hop dense retrieval approach for answering complex open-domain questions, which achieves state-of-the-art performance on two multi-hop datasets, HotpotQA and multi-evidence FEVER. Contrary to previous work, our method does not require access to any corpus-specific information, such as inter-document hyperlinks or human-annotated entity markers, and can be applied to any unstructured text corpus. Our system also yields a much better efficiency-accuracy trade-off, matching the best published accuracy on HotpotQA while being 10 times faster at inference time.

Details

NeurIPS Conference 2021 Conference Paper

Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking

Zhiyi Ma
Kawin Ethayarajh
Tristan Thrush
Somya Jain
Ledell Wu
Robin Jia
Christopher Potts
Adina Williams

We introduce Dynaboard, an evaluation-as-a-service framework for hosting benchmarks and conducting holistic model comparison, integrated with the Dynabench platform. Our platform evaluates NLP models directly instead of relying on self-reported metrics or predictions on a single dataset. Under this paradigm, models are submitted to be evaluated in the cloud, circumventing the issues of reproducibility, accessibility, and backwards compatibility that often hinder benchmarking in NLP. This allows users to interact with uploaded models in real time to assess their quality, and permits the collection of additional metrics such as memory use, throughput, and robustness, which -- despite their importance to practitioners -- have traditionally been absent from leaderboards. On each task, models are ranked according to the Dynascore, a novel utility-based aggregation of these statistics, which users can customize to better reflect their preferences, placing more/less weight on a particular axis of evaluation or dataset. As state-of-the-art NLP models push the limits of traditional benchmarks, Dynaboard offers a standardized solution for a more diverse and comprehensive evaluation of model quality.

PDF Details

NeurIPS Conference 2021 Conference Paper

Human-Adversarial Visual Question Answering

Sasha Sheng
Amanpreet Singh
Vedanuj Goswami
Jose Magana
Tristan Thrush
Wojciech Galuba
Devi Parikh
Douwe Kiela

Performance on the most commonly used Visual Question Answering dataset (VQA v2) is starting to approach human accuracy. However, in interacting with state-of-the-art VQA models, it is clear that the problem is far from being solved. In order to stress test VQA models, we benchmark them against human-adversarial examples. Human subjects interact with a state-of-the-art VQA model, and for each image in the dataset, attempt to find a question where the model’s predicted answer is incorrect. We find that a wide range of state-of-the-art models perform poorly when evaluated on these examples. We conduct an extensive analysis of the collected adversarial examples and provide guidance on future research directions. We hope that this Adversarial VQA (AdVQA) benchmark can help drive progress in the field and advance the state of the art.

PDF Details

ICML Conference 2021 Conference Paper

Rissanen Data Analysis: Examining Dataset Characteristics via Description Length

Ethan Perez
Douwe Kiela
Kyunghyun Cho

We introduce a method to determine if a certain capability helps to achieve an accurate model of given data. We view labels as being generated from the inputs by a program composed of subroutines with different capabilities, and we posit that a subroutine is useful if and only if the minimal program that invokes it is shorter than the one that does not. Since minimum program length is uncomputable, we instead estimate the labels’ minimum description length (MDL) as a proxy, giving us a theoretically-grounded method for analyzing dataset characteristics. We call the method Rissanen Data Analysis (RDA) after the father of MDL, and we showcase its applicability on a wide variety of settings in NLP, ranging from evaluating the utility of generating subquestions before answering a question, to analyzing the value of rationales and explanations, to investigating the importance of different parts of speech, and uncovering dataset gender bias.

Details

NeurIPS Conference 2021 Conference Paper

True Few-Shot Learning with Language Models

Ethan Perez
Douwe Kiela
Kyunghyun Cho

Pretrained language models (LMs) perform well on many tasks even when learning from a few examples, but prior work uses many held-out examples to tune various aspects of learning, such as hyperparameters, training objectives, and natural language templates ("prompts"). Here, we evaluate the few-shot ability of LMs when such held-out examples are unavailable, a setting we call true few-shot learning. We test two model selection criteria, cross-validation and minimum description length, for choosing LM prompts and hyperparameters in the true few-shot setting. On average, both marginally outperform random selection and greatly underperform selection based on held-out examples. Moreover, selection criteria often prefer models that perform significantly worse than randomly-selected ones. We find similar results even when taking into account our uncertainty in a model's true performance during selection, as well as when varying the amount of computation and number of examples used for selection. Overall, our findings suggest that prior work significantly overestimated the true few-shot ability of LMs given the difficulty of few-shot model selection.

PDF Details

AAAI Conference 2020 Conference Paper

Generating Interactive Worlds with Text

Angela Fan
Jack Urbanek
Pratik Ringshia
Emily Dinan
Emma Qian
Siddharth Karamcheti
Shrimai Prabhumoye
Douwe Kiela

Procedurally generating cohesive and interesting game environments is challenging and time-consuming. In order for the relationships between the game elements to be natural, common-sense has to be encoded into arrangement of the elements. In this work, we investigate a machine learning approach for world creation using content from the multiplayer text adventure game environment LIGHT (Urbanek et al. 2019). We introduce neural network based models to compositionally arrange locations, characters, and objects into a coherent whole. In addition to creating worlds based on existing elements, our models can generate new game content. Humans can also leverage our models to interactively aid in worldbuilding. We show that the game environments created with our approach are cohesive, diverse, and preferred by human evaluators compared to other machine learning based world construction algorithms.

PDF Details

NeurIPS Conference 2020 Conference Paper

Learning Optimal Representations with the Decodable Information Bottleneck

Yann Dubois
Douwe Kiela
David J. Schwab
Ramakrishna Vedantam

We address the question of characterizing and finding optimal representations for supervised learning. Traditionally, this question has been tackled using the Information Bottleneck, which compresses the inputs while retaining information about the targets, in a decoder-agnostic fashion. In machine learning, however, our goal is not compression but rather generalization, which is intimately linked to the predictive family or decoder of interest (e. g. linear classifier). We propose the Decodable Information Bottleneck (DIB) that considers information retention and compression from the perspective of the desired predictive family. As a result, DIB gives rise to representations that are optimal in terms of expected test performance and can be estimated with guarantees. Empirically, we show that the framework can be used to enforce a small generalization gap on downstream classifiers and to predict the generalization ability of neural networks.

PDF Details

ICLR Conference 2020 Conference Paper

On the interaction between supervision and self-play in emergent communication

Ryan Lowe
Abhinav Gupta 0002
Jakob N. Foerster
Douwe Kiela
Joelle Pineau

A promising approach for teaching artificial agents to use natural language involves using human-in-the-loop training. However, recent work suggests that current machine learning methods are too data inefficient to be trained in this way from scratch. In this paper, we investigate the relationship between two categories of learning signals with the ultimate goal of improving sample efficiency: imitating human language data via supervised learning, and maximizing reward in a simulated multi-agent environment via self-play (as done in emergent communication), and introduce the term supervised self-play (S2P) for algorithms using both of these signals. We find that first training agents via supervised learning on human data followed by self-play outperforms the converse, suggesting that it is not beneficial to emerge languages from scratch. We then empirically investigate various S2P schedules that begin with supervised learning in two environments: a Lewis signaling game with symbolic inputs, and an image-based referential game with natural language descriptions. Lastly, we introduce population based approaches to S2P, which further improves the performance over single-agent methods.

Details

NeurIPS Conference 2020 Conference Paper

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Patrick Lewis
Ethan Perez
Aleksandra Piktus
Fabio Petroni
Vladimir Karpukhin
Naman Goyal
Heinrich Küttler
Mike Lewis

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.

PDF Details

NeurIPS Conference 2020 Conference Paper

The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes

Douwe Kiela
Hamed Firooz
Aravind Mohan
Vedanuj Goswami
Amanpreet Singh
Pratik Ringshia
Davide Testuggine

This work proposes a new challenge set for multimodal classification, focusing on detecting hate speech in multimodal memes. It is constructed such that unimodal models struggle and only multimodal models can succeed: difficult examples (“benign confounders”) are added to the dataset to make it hard to rely on unimodal signals. The task requires subtle reasoning, yet is straightforward to evaluate as a binary classification problem. We provide baseline performance numbers for unimodal models, as well as for multimodal models with various degrees of sophistication. We find that state-of-the-art methods perform poorly compared to humans, illustrating the difficulty of the task and highlighting the challenge that this important problem poses to the community.

PDF Details

AAAI Conference 2019 Conference Paper

Analysis of Joint Multilingual Sentence Representations and Semantic K-Nearest Neighbor Graphs

Holger Schwenk
Douwe Kiela
Matthijs Douze

Multilingual sentence and document representations are becoming increasingly important. We build on recent advances in multilingual sentence encoders, with a focus on efficiency and large-scale applicability. Specifically, we construct and investigate the k-nn graph over the joint space of 566 million news sentences in seven different languages. We show excellent multilingual retrieval quality on the UN corpus of 11. 3M sentences, which extends to the zero-shot case where we have never seen a language. We provide a detailed analysis of both the multilingual sentence encoder for twenty-one European languages and the learned graph. Our sentence encoder is language agnostic and supports code switching.

PDF Details

NeurIPS Conference 2019 Conference Paper

Hyperbolic Graph Neural Networks

Qi Liu
Maximilian Nickel
Douwe Kiela

Learning from graph-structured data is an important task in machine learning and artificial intelligence, for which Graph Neural Networks (GNNs) have shown great promise. Motivated by recent advances in geometric representation learning, we propose a novel GNN architecture for learning representations on Riemannian manifolds with differentiable exponential and logarithmic maps. We develop a scalable algorithm for modeling the structural properties of graphs, comparing Euclidean and hyperbolic geometry. In our experiments, we show that hyperbolic GNNs can lead to substantial improvements on various benchmark datasets.

PDF Details

AAAI Conference 2018 Conference Paper

Efficient Large-Scale Multi-Modal Classification

Douwe Kiela
Edouard Grave
Armand Joulin
Tomas Mikolov

While the incipient internet was largely text-based, the modern digital world is becoming increasingly multi-modal. Here, we examine multi-modal classification where one modality is discrete, e.g. text, and the other is continuous, e.g. visual representations transferred from a convolutional neural network. In particular, we focus on scenarios where we have to be able to classify large quantities of data quickly. We investigate various methods for performing multi-modal fusion and analyze their trade-offs in terms of classification accuracy and computational efficiency. Our findings indicate that the inclusion of continuous information improves performance over text-only on a range of multi-modal classification tasks, even with simple fusion methods. In addition, we experiment with discretizing the continuous features in order to speed up and simplify the fusion process even further. Our results show that fusion with discretized features outperforms text-only classification, at a fraction of the computational cost of full multi-modal fusion, with the additional benefit of improved interpretability.

PDF Details

ICML Conference 2018 Conference Paper

Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry

Maximilian Nickel
Douwe Kiela

We are concerned with the discovery of hierarchical relationships from large-scale unstructured similarity scores. For this purpose, we study different models of hyperbolic space and find that learning embeddings in the Lorentz model is substantially more efficient than in the Poincar{é}-ball model. We show that the proposed approach allows us to learn high-quality embeddings of large taxonomies which yield improvements over Poincar{é} embeddings, especially in low dimensions. Lastly, we apply our model to discover hierarchies in two real-world datasets: we show that an embedding in hyperbolic space can reveal important aspects of a company’s organizational structure as well as reveal historical relationships between language families.

Details

JAIR Journal 2017 Journal Article

Learning Neural Audio Embeddings for Grounding Semantics in Auditory Perception

Douwe Kiela
Stephen Clark

Multi-modal semantics, which aims to ground semantic representations in perception, has relied on feature norms or raw image data for perceptual input. In this paper we examine grounding semantic representations in raw auditory data, using standard evaluations for multi-modal semantics. After having shown the quality of such auditorily grounded representations, we show how they can be applied to tasks where auditory perception is relevant, including two unsupervised categorization experiments, and provide further analysis. We find that features transfered from deep neural networks outperform bag of audio words approaches. To our knowledge, this is the first work to construct multi-modal models from a combination of textual information and auditory information extracted from deep neural networks, and the first work to evaluate the performance of tri-modal (textual, visual and auditory) semantic models.

PDF Details DOI

NeurIPS Conference 2017 Conference Paper

Poincaré Embeddings for Learning Hierarchical Representations

Maximillian Nickel
Douwe Kiela

Representation learning has become an invaluable approach for learning from symbolic data such as text and graphs. However, state-of-the-art embedding methods typically do not account for latent hierarchical structures which are characteristic for many complex symbolic datasets. In this work, we introduce a new approach for learning hierarchical representations of symbolic data by embedding them into hyperbolic space -- or more precisely into an n-dimensional Poincaré ball. Due to the underlying hyperbolic geometry, this allows us to learn parsimonious representations of symbolic data by simultaneously capturing hierarchy and similarity. We present an efficient algorithm to learn the embeddings based on Riemannian optimization and show experimentally that Poincaré embeddings can outperform Euclidean embeddings significantly on data with latent hierarchies, both in terms of representation capacity and in terms of generalization ability.

PDF Details