🧑‍🔬 Anya Belz

🏛️ Affiliations

🎓Dublin City UniversityDublin · Ireland2022–2026 · 23 paperscurrent🔬ADAPT - Centre for Digital Content TechnologyDublin · Ireland2023–2026 · 4 paperscurrent🎓University of AberdeenAberdeen · United Kingdom2022–2025 · 4 papers

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.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. The Third Multilingual Surface Realisation Shared Task (SR'20): Overview and Evaluation Results (2020 · 18 citations)
   The third edition of the surface realisation task keeps the two tracks of the earlier editions: a shallow track with unordered lemmatised UD trees, and a deep track that also removes function words and morphology.
2. Beyond Outcome Verification: Verifiable Process Reward Models for Structured Reasoning (2026 · 2 citations)
   Reinforcement learning with verifiable rewards (RLVR) has improved LLMs on code and mathematics, but it only checks the final answer.
3. Process Standardisation for Human Evaluation of NLP System Outputs (2026 · 1 citation)
   Running human evaluations of NLP output is demanding. Researchers often lack training in experimental design and must build interfaces, item lists and analysis code themselves for every study. This paper addresses the effort side of that problem by asking whether existing evaluations share enough structure to support…
4. AutoForest: Automatically Generating Forest Plots from Biomedical Studies with End-to-End Evidence Extraction and Synthesis (2026)
   Building forest plots for systematic reviews is still slow, piecemeal work. Reviewers read trial reports, settle on the intervention, comparator and outcome, copy numbers by hand, and then enter structured data into tools such as RevMan. AutoForest is presented as the first system to cover this whole chain, starting…
5. Automatic Paper Analysis and Categorisation for Systematic Reviews with Combined Reasoning-Augmented SFT and DAPO RL (2026)
   Categorising studies along multiple dimensions is one of the most labour-intensive steps of a systematic review, and current LLM-based automation still performs poorly on it.
6. LLM Multi-Agent Systems for Long Triple Set Data-to-Text Generation (2026)
   Most data-to-text (D2T) benchmarks pair short inputs with outputs of a few dozen tokens. As a result, it is unclear how LLMs handle large structured inputs, where single-pass generation tends to omit or invent facts. The authors build a new dataset of 669 DBpedia triple sets, each with 8 to 199 triples, drawn from…

🤝 Co-authors here

12 of 13 co-authors with a page, the most papers together first.

• Simon Mille ×3
• Craig Thomson ×2
• Massimiliano Pronesti ×2
• Thiago Castro Ferreira ×2
• Yufang Hou ×2
• Bernd Bohnet
• Brian Davis
• Elaine Uí Dhonnchadha
• Jane Lauren Adkins
• Leo Wanner
• Mark Andrade
• Ornait O'Connell

Venues

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

• Findings of the Association for Computational Linguistics ×3: Findings of the Association for Computational Linguistics 2026 ×3
• Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2026
• Workshop on Generation, Evaluation and Metrics (GEM): GEM 2026
• Workshop on Multilingual Surface Realisation: Workshop on Multilingual Surface Realisation 2020

🔗 Cited by

Papers of our library cite their works 21 times (of the 149,439 papers whose bibliographies we read); 2 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/anya-belz/