Search Results for author:
Found 20 papers, 14 papers with code
The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models
Natural-language assistants are designed to provide users with helpful responses while avoiding harmful outputs, largely achieved through alignment to human preferences.
Pixtral 12B
Unlike many open-source models, Pixtral is also a cutting-edge text model for its size, and does not compromise on natural language performance to excel in multimodal tasks.
The Llama 3 Herd of Models
This paper presents a new set of foundation models, called Llama 3.
Ranked #2 on
Multi-task Language Understanding
on MMLU
Towards Safety and Helpfulness Balanced Responses via Controllable Large Language Models
As large language models (LLMs) become easily accessible nowadays, the trade-off between safety and helpfulness can significantly impact user experience.
Effective Long-Context Scaling of Foundation Models
We also examine the impact of various design choices in the pretraining process, including the data mix and the training curriculum of sequence lengths -- our ablation experiments suggest that having abundant long texts in the pretrain dataset is not the key to achieving strong performance, and we empirically verify that long context continual pretraining is more efficient and similarly effective compared to pretraining from scratch with long sequences.
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 #34 on
Code Generation
on MBPP
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
Multilingual End to End Entity Linking
Entity Linking is one of the most common Natural Language Processing tasks in practical applications, but so far efficient end-to-end solutions with multilingual coverage have been lacking, leading to complex model stacks.
Polar Ducks and Where to Find Them: Enhancing Entity Linking with Duck Typing and Polar Box Embeddings
Inspired by duck typing in programming languages, we propose to define the type of an entity based on the relations that it has with other entities in a knowledge graph.
Entity Tagging: Extracting Entities in Text Without Mention Supervision
Detection and disambiguation of all entities in text is a crucial task for a wide range of applications.
Efficient Large Scale Language Modeling with Mixtures of Experts
This paper presents a detailed empirical study of how autoregressive MoE language models scale in comparison with dense models in a wide range of settings: in- and out-of-domain language modeling, zero- and few-shot priming, and full-shot fine-tuning.
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.
Les mod\`eles de langue contextuels Camembert pour le fran\ccais : impact de la taille et de l'h\'et\'erog\'en\'eit\'e des donn\'ees d'entrainement (C AMEM BERT Contextual Language Models for French: Impact of Training Data Size and Heterogeneity )
L{'}utilisation pratique de ces mod{\`e}les {---} dans toutes les langues sauf l{'}anglais {---} {\'e}tait donc limit{\'e}e. La sortie r{\'e}cente de plusieurs mod{\`e}les monolingues fond{\'e}s sur BERT (Devlin et al., 2019), notamment pour le fran{\c{c}}ais, a d{\'e}montr{\'e} l{'}int{\'e}r{\^e}t de ces mod{\`e}les en am{\'e}liorant l{'}{\'e}tat de l{'}art pour toutes les t{\^a}ches {\'e}valu{\'e}es.
ASSET: A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformations
Furthermore, we motivate the need for developing better methods for automatic evaluation using ASSET, since we show that current popular metrics may not be suitable when multiple simplification transformations are performed.
MUSS: Multilingual Unsupervised Sentence Simplification by Mining Paraphrases
Progress in sentence simplification has been hindered by a lack of labeled parallel simplification data, particularly in languages other than English.
Ranked #2 on
Text Simplification
on ASSET
CamemBERT: a Tasty French Language Model
We show that the use of web crawled data is preferable to the use of Wikipedia data.
Ranked #1 on
Natural Language Inference
on XNLI French
Controllable Sentence Simplification
Text simplification aims at making a text easier to read and understand by simplifying grammar and structure while keeping the underlying information identical.
Ranked #3 on
Text Simplification
on ASSET
EASSE: Easier Automatic Sentence Simplification Evaluation
We introduce EASSE, a Python package aiming to facilitate and standardise automatic evaluation and comparison of Sentence Simplification (SS) systems.
Reference-less Quality Estimation of Text Simplification Systems
We show that n-gram-based MT metrics such as BLEU and METEOR correlate the most with human judgment of grammaticality and meaning preservation, whereas simplicity is best evaluated by basic length-based metrics.
ELMoLex: Connecting ELMo and Lexicon Features for Dependency Parsing
We augment the deep Biaffine (BiAF) parser (Dozat and Manning, 2016) with novel features to perform competitively: we utilize an indomain version of ELMo features (Peters et al., 2018) which provide context-dependent word representations; we utilize disambiguated, embedded, morphosyntactic features from lexicons (Sagot, 2018), which complements the existing feature set.
