Search Results for author:
Found 36 papers, 24 papers with code
Nougat: Neural Optical Understanding for Academic Documents
Scientific knowledge is predominantly stored in books and scientific journals, often in the form of PDFs.
Optical Character Recognition
Optical Character Recognition (OCR)
Llama 2: Open Foundation and Fine-Tuned Chat Models
In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters.
Ranked #2 on
Question Answering
on PubChemQA
Discriminative Adversarial Search for Abstractive Summarization
We introduce a novel approach for sequence decoding, Discriminative Adversarial Search (DAS), which has the desirable properties of alleviating the effects of exposure bias without requiring external metrics.
Synthetic Data Augmentation for Zero-Shot Cross-Lingual Question Answering
Coupled with the availability of large scale datasets, deep learning architectures have enabled rapid progress on the Question Answering task.
Code Llama: Open Foundation Models for Code
We release Code Llama, a family of large language models for code based on Llama 2 providing state-of-the-art performance among open models, infilling capabilities, support for large input contexts, and zero-shot instruction following ability for programming tasks.
Ranked #26 on
Code Generation
on MBPP
Galactica: A Large Language Model for Science
We believe these results demonstrate the potential for language models as a new interface for science.
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions.
NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation
Data augmentation is an important component in the robustness evaluation of models in natural language processing (NLP) and in enhancing the diversity of the data they are trained on.
Augmented Language Models: a Survey
This survey reviews works in which language models (LMs) are augmented with reasoning skills and the ability to use tools.
Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor
We collect 64, 000 examples by prompting a language model with three seed examples of instructions and eliciting a fourth.
Project PIAF: Building a Native French Question-Answering Dataset
Motivated by the lack of data for non-English languages, in particular for the evaluation of downstream tasks such as Question Answering, we present a participatory effort to collect a native French Question Answering Dataset.
Ranked #4 on
Question Answering
on FQuAD
(using extra training data)
QuestEval: Summarization Asks for Fact-based Evaluation
Summarization evaluation remains an open research problem: current metrics such as ROUGE are known to be limited and to correlate poorly with human judgments.
Rethinking Automatic Evaluation in Sentence Simplification
In the context of Sentence Simplification, this is particularly challenging: the task requires by nature to replace complex words with simpler ones that shares the same meaning.
Data-QuestEval: A Referenceless Metric for Data-to-Text Semantic Evaluation
QuestEval is a reference-less metric used in text-to-text tasks, that compares the generated summaries directly to the source text, by automatically asking and answering questions.
TRUE: Re-evaluating Factual Consistency Evaluation
Grounded text generation systems often generate text that contains factual inconsistencies, hindering their real-world applicability.
Which Discriminator for Cooperative Text Generation?
Language models generate texts by successively predicting probability distributions for next tokens given past ones.
Fine-tuned Language Models are Continual Learners
In spite of the limited success of Continual Learning we show that Language Models can be continual learners.
BEAMetrics: A Benchmark for Language Generation Evaluation Evaluation
There is currently no simple, unified way to compare, analyse or evaluate metrics across a representative set of tasks.
WorldSense: A Synthetic Benchmark for Grounded Reasoning in Large Language Models
We propose WorldSense, a benchmark designed to assess the extent to which LLMs are consistently able to sustain tacit world models, by testing how they draw simple inferences from descriptions of simple arrangements of entities.
Answers Unite! Unsupervised Metrics for Reinforced Summarization Models
Abstractive summarization approaches based on Reinforcement Learning (RL) have recently been proposed to overcome classical likelihood maximization.
RQUGE: Reference-Free Metric for Evaluating Question Generation by Answering the Question
We demonstrate that RQUGE has a higher correlation with human judgment without relying on the reference question.
Skim-Attention: Learning to Focus via Document Layout
Motivated by human reading strategies, this paper presents Skim-Attention, a new attention mechanism that takes advantage of the structure of the document and its layout.
LoRaLay: A Multilingual and Multimodal Dataset for Long Range and Layout-Aware Summarization
Text Summarization is a popular task and an active area of research for the Natural Language Processing community.
Self-Attention Architectures for Answer-Agnostic Neural Question Generation
Neural architectures based on self-attention, such as Transformers, recently attracted interest from the research community, and obtained significant improvements over the state of the art in several tasks.
Ask to Learn: A Study on Curiosity-driven Question Generation
We propose a novel text generation task, namely Curiosity-driven Question Generation.
Conversational Question Answering
Machine Reading Comprehension
+3
What BERT Sees: Cross-Modal Transfer for Visual Question Generation
Pre-trained language models have recently contributed to significant advances in NLP tasks.
MLSUM: The Multilingual Summarization Corpus
We present MLSUM, the first large-scale MultiLingual SUMmarization dataset.
ColdGANs: Taming Language GANs with Cautious Sampling Strategies
Training regimes based on Maximum Likelihood Estimation (MLE) suffer from known limitations, often leading to poorly generated text sequences.
Toward Stance-based Personas for Opinionated Dialogues
In the context of chit-chat dialogues it has been shown that endowing systems with a persona profile is important to produce more coherent and meaningful conversations.
To Beam Or Not To Beam: That is a Question of Cooperation for Language GANs
Due to the discrete nature of words, language GANs require to be optimized from rewards provided by discriminator networks, via reinforcement learning methods.
Generative Cooperative Networks for Natural Language Generation
Generative Adversarial Networks (GANs) have known a tremendous success for many continuous generation tasks, especially in the field of image generation.
MaskEval: Weighted MLM-Based Evaluation for Text Summarization and Simplification
In text summarization and simplification, system outputs must be evaluated along multiple dimensions such as relevance, factual consistency, fluency, and grammaticality, and a wide range of possible outputs could be of high quality.
Choisir le bon co-équipier pour la génération coopérative de texte (Choosing The Right Teammate For Cooperative Text Generation)
Nous évaluons leurs avantages et inconvénients, en explorant leur précision respective sur des tâches de classification, ainsi que leur impact sur la génération coopérative et leur coût de calcul, dans le cadre d’une stratégie de décodage état de l’art, basée sur une recherche arborescente de Monte-Carlo (MCTS).
GAIA: a benchmark for General AI Assistants
GAIA's philosophy departs from the current trend in AI benchmarks suggesting to target tasks that are ever more difficult for humans.
Toolformer: Language Models Can Teach Themselves to Use Tools
Language models (LMs) exhibit remarkable abilities to solve new tasks from just a few examples or textual instructions, especially at scale.
