33 citations · 56 across the 19 of their papers we have counts for
20 papers
An Actionable Diagnosis of Multilingual, Multi-Agent Planning Failures
Vikas Pahuja, Jonathan Brokman, Omer Hofman +6
Multilingual multi-agent systems exhibit substantial degradation beyond English, yet prior work rarely identifies how task-critical information is lost when user requests are conve…
The Multilingual Divide and Its Impact on Global AI Safety
Aidan Peppin, Julia Kreutzer, Alice Schoenauer Sebag +13
Despite advances in large language model capabilities in recent years, a large gap remains in their capabilities and safety performance for many languages beyond a relatively small…
MAPS: A Multilingual Benchmark for Agent Performance and Security
Omer Hofman, Jonathan Brokman, Oren Rachmil +7
Agentic AI systems, which build on Large Language Models (LLMs) and interact with tools and memory, have rapidly advanced in capability and scope. Yet, since LLMs have been shown t…
Command A: An Enterprise-Ready Large Language Model
Team Cohere, :, Aakanksha +227
In this report we describe the development of Command A, a powerful large language model purpose-built to excel at real-world enterprise use cases. Command A is an agent-optimised…
The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs
Piotr Nawrot, Robert Li, Renjie Huang +3
Sparse attention offers a promising strategy to extend long-context capabilities in Transformer LLMs, yet its efficiency-accuracy trade-offs remain unclear due to the lack of compr…
AL-QASIDA: Analyzing LLM Quality and Accuracy Systematically in Dialectal Arabic
Nathaniel R. Robinson, Shahd Abdelmoneim, Kelly Marchisio +1
Dialectal Arabic (DA) varieties are under-served by language technologies, particularly large language models (LLMs). This trend threatens to exacerbate existing social inequalitie…
Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation
Shivalika Singh, Angelika Romanou, Clémentine Fourrier +21
Cultural biases in multilingual datasets pose significant challenges for their effectiveness as global benchmarks. These biases stem not only from differences in language but also…
RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs
John Dang, Arash Ahmadian, Kelly Marchisio +3
Preference optimization techniques have become a standard final stage for training state-of-art large language models (LLMs). However, despite widespread adoption, the vast majorit…
How Does Quantization Affect Multilingual LLMs?
Kelly Marchisio, Saurabh Dash, Hongyu Chen +4
Quantization techniques are widely used to improve inference speed and deployment of large language models. While a wide body of work examines the impact of quantization on LLMs in…
Understanding and Mitigating Language Confusion in LLMs
Kelly Marchisio, Wei-Yin Ko, Alexandre Bérard +2
We investigate a surprising limitation of LLMs: their inability to consistently generate text in a user's desired language. We create the Language Confusion Benchmark (LCB) to eval…
Aya 23: Open Weight Releases to Further Multilingual Progress
Viraat Aryabumi, John Dang, Dwarak Talupuru +18
This technical report introduces Aya 23, a family of multilingual language models. Aya 23 builds on the recent release of the Aya model (Üstün et al., 2024), focusing on pairing a…
Improving Language Plasticity via Pretraining with Active Forgetting
Yihong Chen, Kelly Marchisio, Roberta Raileanu +4
Pretrained language models (PLMs) are today the primary model for natural language processing. Despite their impressive downstream performance, it can be difficult to apply PLMs to…
Learning a Formality-Aware Japanese Sentence Representation
Henry Li Xinyuan, Ray Lee, Jerry Chen +1
While the way intermediate representations are generated in encoder-decoder sequence-to-sequence models typically allow them to preserve the semantics of the input sentence, input…
Mini-Model Adaptation: Efficiently Extending Pretrained Models to New Languages via Aligned Shallow Training
Kelly Marchisio, Patrick Lewis, Yihong Chen +1
Prior work shows that it is possible to expand pretrained Masked Language Models (MLMs) to new languages by learning a new set of embeddings, while keeping the transformer body fro…
Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transport
Kelly Marchisio, Ali Saad-Eldin, Kevin Duh +2
Bilingual lexicons form a critical component of various natural language processing applications, including unsupervised and semisupervised machine translation and crosslingual inf…
IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces
Kelly Marchisio, Neha Verma, Kevin Duh +1
The ability to extract high-quality translation dictionaries from monolingual word embedding spaces depends critically on the geometric similarity of the spaces -- their degree of…
An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding Spaces
Kelly Marchisio, Youngser Park, Ali Saad-Eldin +4
Much recent work in bilingual lexicon induction (BLI) views word embeddings as vectors in Euclidean space. As such, BLI is typically solved by finding a linear transformation that…
On Systematic Style Differences between Unsupervised and Supervised MT and an Application for High-Resource Machine Translation
Kelly Marchisio, Markus Freitag, David Grangier
Modern unsupervised machine translation (MT) systems reach reasonable translation quality under clean and controlled data conditions. As the performance gap between supervised and…
Embedding-Enhanced Giza++: Improving Alignment in Low- and High- Resource Scenarios Using Embedding Space Geometry
Kelly Marchisio, Conghao Xiong, Philipp Koehn
A popular natural language processing task decades ago, word alignment has been dominated until recently by GIZA++, a statistical method based on the 30-year-old IBM models. New me…
When Does Unsupervised Machine Translation Work?
Kelly Marchisio, Kevin Duh, Philipp Koehn
Despite the reported success of unsupervised machine translation (MT), the field has yet to examine the conditions under which these methods succeed, and where they fail. We conduc…