--- title: "Nuno M. Guerreiro — author profile and papers" description: "Nuno M. Guerreiro: 8 papers on Elamur Research (2022–2024), h-index 6 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/nuno-m-guerreiro/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/nuno-m-guerreiro/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Nuno M. Guerreiro # Nuno M. Guerreiro Nuno M. Guerreiro works on [machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/), with a focus on how translation quality is measured and how translation systems fail. Their papers here return to a few linked questions: how to score a translation, sometimes without any reference text, how to locate and grade individual errors, and how to detect hallucinations, where the output loses its link to the source sentence. More recently the work has also turned to building open multilingual language models for translation and related tasks. The most cited of these papers is [xCOMET](https://md.research.elamur.ai/free/en/papers/guerreiro-2024-xcomet-transparent-machine-translation-evaluation/) (2024). It is an open learned metric that gives a quality score and also marks error spans by severity, then merges the two signals into one judgement. CometKiwi (2022) describes a quality estimation system that IST and Unbabel submitted together to WMT that year, taking part in all three subtasks. A 2023 follow-up scaled it up, and Guerreiro also co-authored the findings report for that year's task. Two 2023 studies deal with hallucinations. [Looking for a Needle in a Haystack](https://md.research.elamur.ai/free/en/papers/guerreiro-2023-looking-needle-haystack-comprehensive-study/) examines naturally occurring cases in neural MT, without injected noise, and proposes a taxonomy of detached and oscillatory types. [Hallucinations in Large Multilingual Translation Models](https://md.research.elamur.ai/free/en/papers/guerreiro-2023-hallucinations-large-multilingual-translation-models/) carries the question to large multilingual systems and to ChatGPT and GPT-4, across more than 100 translation directions. The newest papers move from evaluating translation systems to building them. [Tower](https://md.research.elamur.ai/free/en/papers/alves-2024-tower-open-multilingual-large-language/) (2024) continues the pretraining of LLaMA-2 on text in ten languages and then instruction-tunes it, so that one open model can handle a whole translation workflow. [EuroLLM](https://md.research.elamur.ai/free/en/papers/martins-2024-eurollm-multilingual-language-models-europe/) (2024) reports on the first models of a project covering every official EU language and several others. Bylines from 2019 to 2023 list the [Instituto Superior Técnico](https://md.research.elamur.ai/free/en/universities/instituto-superior-tecnico/), the [Instituto de Telecomunicações](https://md.research.elamur.ai/free/en/labs/instituto-de-telecomunicacoes/) and the [University of Lisbon](https://md.research.elamur.ai/free/en/universities/university-of-lisbon/), all in Lisbon. The most frequent co-authors on these papers are [André F. T. Martins](https://md.research.elamur.ai/free/en/authors/andre-f-t-martins/) and [Ricardo Rei](https://md.research.elamur.ai/free/en/authors/ricardo-rei/), with José G. C. de Souza and Pierre Colombo also appearing often. Beyond translation, the papers fall under multilingual NLP and evaluation and benchmarks. Nuno M. Guerreiro has 8 papers in our library, in 2022–2024, most of them on [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/), [Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/), [Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/); often with [André F. T. Martins](https://md.research.elamur.ai/free/en/authors/andre-f-t-martins/), [Ricardo Rei](https://md.research.elamur.ai/free/en/authors/ricardo-rei/), [José G. C. de Souza](https://md.research.elamur.ai/free/en/authors/jose-g-c-de-souza/). 8 papers in our library · 2022–2024 [OpenAlex](https://openalex.org/A5027738462) · [ORCID](https://orcid.org/0000-0001-6105-9354) · [**h-index 6**](https://openalex.org/authors/A5027738462) · [9 works](https://openalex.org/works?filter=author.id:A5027738462) · [79 citations](https://openalex.org/works?filter=author.id:A5027738462&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 8 works in our library](https://md.research.elamur.ai/free/en/authors/nuno-m-guerreiro/#papers) · [🔗 1,356 citations in our library](https://md.research.elamur.ai/free/en/authors/nuno-m-guerreiro/cited-by/) · [2 more in our library without a page yet](#also) · [⭐ Paper Star rank #1377](https://md.research.elamur.ai/free/en/paper-stars/page/14/#star-1377) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Nuno+M.+Guerreiro) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Nuno+M.+Guerreiro) · [dblp](https://dblp.org/search?q=Nuno+M.+Guerreiro) · [ACL Anthology](https://aclanthology.org/search/?q=Nuno+M.+Guerreiro) ## Affiliations [🔬**Instituto de Telecomunicações** Lisbon · Portugal 2021–2023 · 7 papers](https://md.research.elamur.ai/free/en/labs/instituto-de-telecomunicacoes/) · [🎓**Instituto Superior Técnico** Lisbon · Portugal 2019–2023 · 6 papers](https://md.research.elamur.ai/free/en/universities/instituto-superior-tecnico/) · [🎓**University of Lisbon** Lisbon · Portugal 2019–2023 · 4 papers](https://md.research.elamur.ai/free/en/universities/university-of-lisbon/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed. ## Topics [Machine translation (5)](https://md.research.elamur.ai/free/en/topics/machine-translation/) · [Multilingual & cross-lingual NLP (3)](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · [Evaluation & benchmarks (2)](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · [Language models & pretraining (1)](https://md.research.elamur.ai/free/en/topics/language-models/) ## Works by year ### 2020s [**2024** 3 papers](https://md.research.elamur.ai/free/en/authors/nuno-m-guerreiro/year/2024/) · [**2023** 4 papers](https://md.research.elamur.ai/free/en/authors/nuno-m-guerreiro/year/2023/) · [**2022** 1 paper](https://md.research.elamur.ai/free/en/papers/rei-2022-cometkiwi-ist-unbabel-2022-submission/) ## Papers The most cited first (OpenAlex and our library). 1. **[xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection](https://md.research.elamur.ai/free/en/papers/guerreiro-2024-xcomet-transparent-machine-translation-evaluation/)** *(2024 · 333 citations)* Neural metrics for machine translation evaluation, such as COMET and BLEURT, usually output one sentence-level number. 2. **[CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task](https://md.research.elamur.ai/free/en/papers/rei-2022-cometkiwi-ist-unbabel-2022-submission/)** *(2022 · 325 citations)* This paper describes the joint IST and Unbabel entry to the WMT 2022 Quality Estimation shared task. Quality Estimation (QE) scores machine translation output without reference translations. The team entered all three subtasks: sentence- and word-level quality prediction, Explainable QE, and Critical Error Detection. 3. **[Hallucinations in Large Multilingual Translation Models](https://md.research.elamur.ai/free/en/papers/guerreiro-2023-hallucinations-large-multilingual-translation-models/)** *(2023 · 244 citations)* Earlier studies of hallucinations in machine translation, meaning outputs that lose their connection to the source, looked almost only at small bilingual systems (under 100M parameters) for a single high-resource, English-centric pair. 4. **[Tower: An Open Multilingual Large Language Model for Translation-Related Tasks](https://md.research.elamur.ai/free/en/papers/alves-2024-tower-open-multilingual-large-language/)** *(2024 · 226 citations)* Open LLMs, which are mostly trained on English, have so far matched closed systems only when tuned for one translation-related task. 5. **[Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/guerreiro-2023-looking-needle-haystack-comprehensive-study/)** *(2023 · 147 citations)* Hallucinations in NMT are rare but severe: translations whose content drifts away from the source. Earlier studies mostly made them more frequent artificially, through noisy data, perturbed inputs or domain shift. They also used inconsistent definitions and seldom checked whether their detectors actually work.… 6. **[Scaling up CometKiwi: Unbabel-IST 2023 Submission for the Quality Estimation Shared Task](https://md.research.elamur.ai/free/en/papers/rei-2023-scaling-up-cometkiwi-unbabel-ist/)** *(2023 · 135 citations)* Quality Estimation (QE) scores machine translation output without a reference translation. This paper describes the Unbabel–IST entry to the WMT 2023 QE shared task. Task 1 asked for quality predictions at both the sentence and word level, while Task 2 required pinpointing individual error spans and labelling each… 7. **[EuroLLM: Multilingual Language Models for Europe](https://md.research.elamur.ai/free/en/papers/martins-2024-eurollm-multilingual-language-models-europe/)** *(2024 · 131 citations)* Open-weight LLMs such as LLaMA, Mistral and Gemma mostly serve English and a few major languages, leaving many European languages underserved. 8. **[Findings of the WMT 2023 Shared Task on Quality Estimation](https://md.research.elamur.ai/free/en/papers/blain-2023-findings-wmt-2023-shared-task/)** *(2023 · 129 citations)* The WMT 2023 Quality Estimation shared task benchmarks systems that judge neural MT output without reference translations, at both sentence and word level. ## Also in our library 2 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 12 of 26 co-authors with a page, the most papers together first. - [André F. T. Martins](https://md.research.elamur.ai/free/en/authors/andre-f-t-martins/) ×6 - [Ricardo Rei](https://md.research.elamur.ai/free/en/authors/ricardo-rei/) ×6 - [José G. C. de Souza](https://md.research.elamur.ai/free/en/authors/jose-g-c-de-souza/) ×4 - [Pierre Colombo](https://md.research.elamur.ai/free/en/authors/pierre-colombo/) ×4 - [Duarte M. Alves](https://md.research.elamur.ai/free/en/authors/duarte-m-alves/) ×3 - [Jose Pombal](https://md.research.elamur.ai/free/en/authors/jose-pombal/) ×3 - [Luisa Coheur](https://md.research.elamur.ai/free/en/authors/luisa-coheur/) ×3 - [Amin Farajian](https://md.research.elamur.ai/free/en/authors/amin-farajian/) ×2 - [Barry Haddow](https://md.research.elamur.ai/free/en/authors/barry-haddow/) ×2 - [Chrysoula Zerva](https://md.research.elamur.ai/free/en/authors/chrysoula-zerva/) ×2 - [Daan van Stigt](https://md.research.elamur.ai/free/en/authors/daan-van-stigt/) ×2 - [Joao Alves](https://md.research.elamur.ai/free/en/authors/joao-alves/) ×2 ## Cited by Papers of our library cite their works 1,356 times (of the 140,884 papers whose bibliographies we read); [106 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/nuno-m-guerreiro/cited-by/).