Elamur Research⌕
☰
home / authors / Barry O'Sullivan

Barry O'Sullivan

Barry O'Sullivan has 4 papers in our library, in 2024–2026, most of them on Language models & pretraining, Multilingual & cross-lingual NLP, Evaluation & benchmarks; often with Hoang D. Nguyen, Khanh-Tung Tran.

4 papers in our library · 2024–2026

OpenAlex · h-index 1 · 9 works · 4 citations OpenAlex, 2026-10-14

📄 4 works in our library · 🔗 Cited 13 times in our library · ⭐ Paper Stars ranking: #9422

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓University College CorkCork · Ireland2026 · 2 paperscurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 4 worksArts and Humanities · 4 worksComputer Science · 4 worksLanguage and Linguistics · 4 worksSocial Sciences · 1 workSociology and Political Science · 1 work

🧭 Topics 3Research subjects and languages the work is about.Language models & pretraining · 3 worksEvaluation & benchmarks · 1 workMultilingual & cross-lingual NLP · 1 work

 Works by year

2020s

20263 papers20241 paper

 Papers

The most cited first (OpenAlex and our library).

  1. UCCIX: Irish-eXcellence Large Language Model (2024 · 14 citations)
    Irish is a UNESCO "definitely endangered" language with only a few hundred million tokens of available text, far below what scaling laws suggest for training an LLM.
  2. Disentangling Continued Pre-Training: Attention-Driven Routing and Semantic Hub Preservation in Language Adaptation (2026 · 1 citation)
    The paper examines what happens inside an LLM during Continued Pre-Training (CPT), the process that teaches it a second language. The authors trace the full training trajectory instead of only the final checkpoint. They use English as the base language and three targets: Irish, Basque, and Chinese. The models are:
  3. LaCoMSA: Language-Consistency Multilingual Self-Alignment with Latent Representation Rewarding (2026)
    Multilingual LLMs tend to answer worse in lower-resource languages than in English. They also often switch into English even when prompted in another language. Earlier preference-optimization fixes such as MAPO, LIDR and ICR depend on outside supervision, such as translation systems or English-trained reward models.
  4. Questionnaire Meets LLM: A Benchmark and Empirical Study of Structural Skills for Understanding Questions and Responses (2026)
    Survey data is a grid of respondents by questions. It is hard for LLMs because cells mix types such as Likert scores, coded multiple-choice options and free text, and answer codes must be decoded through schema metadata. Practitioners also have no evidence on how to turn such data into text for a model. The authors…

 Co-authors here

2 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 13 times (of the 149,439 papers whose bibliographies we read); 3 citing papers with a page here →.

Updated

This page in Markdown → https://md.research.elamur.ai/free/en/authors/barry-o-sullivan/