Publications (34)
M-Prometheus: A Suite of Open Multilingual LLM Judges
José Pombal, Dongkeun Yoon, Patrick Fernandes +5
The use of language models for automatically evaluating long-form text (LLM-as-a-judge) is becoming increasingly common, yet most LLM judges are optimized exclusively for English,…
The Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation
Patrick Fernandes, Daniel Deutsch, Mara Finkelstein +7
Automatic evaluation of machine translation (MT) is a critical tool driving the rapid iterative development of MT systems. While considerable progress has been made on estimating a…
Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum Bayes Risk Decoding for Machine Translation
Markus Freitag, Behrooz Ghorbani, Patrick Fernandes
Recent advances in machine translation (MT) have shown that Minimum Bayes Risk (MBR) decoding can be a powerful alternative to beam search decoding, especially when combined with n…
CMU's IWSLT 2024 Simultaneous Speech Translation System
Xi Xu, Siqi Ouyang, Brian Yan +5
This paper describes CMU's submission to the IWSLT 2024 Simultaneous Speech Translation (SST) task for translating English speech to German text in a streaming manner. Our end-to-e…
CroissantLLM: A Truly Bilingual French-English Language Model
Manuel Faysse, Patrick Fernandes, Nuno M. Guerreiro +13
We introduce CroissantLLM, a 1.3B language model pretrained on a set of 3T English and French tokens, to bring to the research and industrial community a high-performance, fully op…
Modeling User Preferences with Automatic Metrics: Creating a High-Quality Preference Dataset for Machine Translation
Sweta Agrawal, José G. C. de Souza, Ricardo Rei +5
Alignment with human preferences is an important step in developing accurate and safe large language models. This is no exception in machine translation (MT), where better handling…
Quality-Aware Decoding for Neural Machine Translation
Patrick Fernandes, António Farinhas, Ricardo Rei +4
Despite the progress in machine translation quality estimation and evaluation in the last years, decoding in neural machine translation (NMT) is mostly oblivious to this and center…
DOCE: Finding the Sweet Spot for Execution-Based Code Generation
Haau-Sing Li, Patrick Fernandes, Iryna Gurevych +1
Recently, a diverse set of decoding and reranking procedures have been shown effective for LLM-based code generation. However, a comprehensive framework that links and experimental…
Scaling Laws for Multilingual Neural Machine Translation
Patrick Fernandes, Behrooz Ghorbani, Xavier Garcia +2
In this work, we provide a large-scale empirical study of the scaling properties of multilingual neural machine translation models. We examine how increases in the model size affec…
TowerVision: Understanding and Improving Multilinguality in Vision-Language Models
André G. Viveiros, Patrick Fernandes, Saul Santos +7
Despite significant advances in vision-language models (VLMs), most existing work follows an English-centric design process, limiting their effectiveness in multilingual settings.…
Not-Just-Scaling Laws: Towards a Better Understanding of the Downstream Impact of Language Model Design Decisions
Emmy Liu, Amanda Bertsch, Lintang Sutawika +9
Improvements in language model capabilities are often attributed to increasing model size or training data, but in some cases smaller models trained on curated data or with differe…
Do LLMs Understand Your Translations? Evaluating Paragraph-level MT with Question Answering
Patrick Fernandes, Sweta Agrawal, Emmanouil Zaranis +2
Despite the steady progress in machine translation evaluation, existing automatic metrics struggle to capture how well meaning is preserved beyond sentence boundaries. We posit tha…
ESPnet-ST-v2: Multipurpose Spoken Language Translation Toolkit
Brian Yan, Jiatong Shi, Yun Tang +13
ESPnet-ST-v2 is a revamp of the open-source ESPnet-ST toolkit necessitated by the broadening interests of the spoken language translation community. ESPnet-ST-v2 supports 1) offlin…
Aligning Neural Machine Translation Models: Human Feedback in Training and Inference
Miguel Moura Ramos, Patrick Fernandes, António Farinhas +1
Reinforcement learning from human feedback (RLHF) is a recent technique to improve the quality of the text generated by a language model, making it closer to what humans would gene…
A Context-aware Framework for Translation-mediated Conversations
José Pombal, Sweta Agrawal, Patrick Fernandes +2
Automatic translation systems offer a powerful solution to bridge language barriers in scenarios where participants do not share a common language. However, these systems can intro…
Measuring and Increasing Context Usage in Context-Aware Machine Translation
Patrick Fernandes, Kayo Yin, Graham Neubig +1
Recent work in neural machine translation has demonstrated both the necessity and feasibility of using inter-sentential context -- context from sentences other than those currently…
Context-aware Neural Machine Translation for English-Japanese Business Scene Dialogues
Sumire Honda, Patrick Fernandes, Chrysoula Zerva
Despite the remarkable advancements in machine translation, the current sentence-level paradigm faces challenges when dealing with highly-contextual languages like Japanese. In thi…
Tower: An Open Multilingual Large Language Model for Translation-Related Tasks
Duarte M. Alves, José Pombal, Nuno M. Guerreiro +10
While general-purpose large language models (LLMs) demonstrate proficiency on multiple tasks within the domain of translation, approaches based on open LLMs are competitive only wh…
When Does Translation Require Context? A Data-driven, Multilingual Exploration
Patrick Fernandes, Kayo Yin, Emmy Liu +2
Although proper handling of discourse significantly contributes to the quality of machine translation (MT), these improvements are not adequately measured in common translation qua…
Do Context-Aware Translation Models Pay the Right Attention?
Kayo Yin, Patrick Fernandes, Danish Pruthi +3
Context-aware machine translation models are designed to leverage contextual information, but often fail to do so. As a result, they inaccurately disambiguate pronouns and polysemo…
Better Instruction-Following Through Minimum Bayes Risk
Ian Wu, Patrick Fernandes, Amanda Bertsch +3
General-purpose LLM judges capable of human-level evaluation provide not only a scalable and accurate way of evaluating instruction-following LLMs but also new avenues for supervis…
Multilingual Contextualization of Large Language Models for Document-Level Machine Translation
Miguel Moura Ramos, Patrick Fernandes, Sweta Agrawal +1
Large language models (LLMs) have demonstrated strong performance in sentence-level machine translation, but scaling to document-level translation remains challenging, particularly…
Learning to Scaffold: Optimizing Model Explanations for Teaching
Patrick Fernandes, Marcos Treviso, Danish Pruthi +2
Modern machine learning models are opaque, and as a result there is a burgeoning academic subfield on methods that explain these models' behavior. However, what is the precise goal…
EuroBERT: Scaling Multilingual Encoders for European Languages
Nicolas Boizard, Hippolyte Gisserot-Boukhlef, Duarte M. Alves +16
General-purpose multilingual vector representations, used in retrieval, regression and classification, are traditionally obtained from bidirectional encoder models. Despite their w…
EuroLLM-9B: Technical Report
Pedro Henrique Martins, João Alves, Patrick Fernandes +14
This report presents EuroLLM-9B, a large language model trained from scratch to support the needs of European citizens by covering all 24 official European Union languages and 11 a…
Structured Neural Summarization
Patrick Fernandes, Miltiadis Allamanis, Marc Brockschmidt
Summarization of long sequences into a concise statement is a core problem in natural language processing, requiring non-trivial understanding of the input. Based on the promising…
Multi-Dimensional Evaluation of Text Summarization with In-Context Learning
Sameer Jain, Vaishakh Keshava, Swarnashree Mysore Sathyendra +4
Evaluation of natural language generation (NLG) is complex and multi-dimensional. Generated text can be evaluated for fluency, coherence, factuality, or any other dimensions of int…
Is Context Helpful for Chat Translation Evaluation?
Sweta Agrawal, Amin Farajian, Patrick Fernandes +2
Despite the recent success of automatic metrics for assessing translation quality, their application in evaluating the quality of machine-translated chats has been limited. Unlike…
EuroLLM: Multilingual Language Models for Europe
Pedro Henrique Martins, Patrick Fernandes, João Alves +12
The quality of open-weight LLMs has seen significant improvement, yet they remain predominantly focused on English. In this paper, we introduce the EuroLLM project, aimed at develo…
Predicting Attention Sparsity in Transformers
Marcos Treviso, António Góis, Patrick Fernandes +2
Transformers' quadratic complexity with respect to the input sequence length has motivated a body of work on efficient sparse approximations to softmax. An alternative path, used b…
A Multi-dimensional Evaluation of Tokenizer-free Multilingual Pretrained Models
Jimin Sun, Patrick Fernandes, Xinyi Wang +1
Recent work on tokenizer-free multilingual pretrained models show promising results in improving cross-lingual transfer and reducing engineering overhead (Clark et al., 2022; Xue e…
Fine-Grained Reward Optimization for Machine Translation using Error Severity Mappings
Miguel Moura Ramos, Tomás Almeida, Daniel Vareta +4
Reinforcement learning (RL) has been proven to be an effective and robust method for training neural machine translation systems, especially when paired with powerful reward models…
Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation
Patrick Fernandes, Aman Madaan, Emmy Liu +8
Many recent advances in natural language generation have been fueled by training large language models on internet-scale data. However, this paradigm can lead to models that genera…
EuroLLM-22B: Technical Report
Miguel Moura Ramos, Duarte M. Alves, Hippolyte Gisserot-Boukhlef +15
This report presents EuroLLM-22B, a large language model trained from scratch to support the needs of European citizens by covering all 24 official European Union languages and 11…