Elamur Research⌕
☰
home / authors / Filip Trhlík

Filip Trhlík

Filip Trhlík has 2 papers in our library, in 2024–2026, most of them on Language models & pretraining, Evaluation & benchmarks, Bias, fairness & safety; often with Alyssa Hwang, Andrew Caines, Andrew Zhu.

2 papers in our library · 2024–2026

OpenAlex · h-index 2 · 13 works · 52 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 65 times in our library · ⭐ Paper Stars ranking: #6691

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 of CambridgeCambridge · United Kingdom2024–2026 · 5 paperscurrent🎓University College LondonLondon · United Kingdom2022–2024 · 4 papers🎓King's College LondonLondon · United Kingdom2024 · 2 papers🎓Charles UniversityPrague · Czechia2022–2023 · 2 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.

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksLanguage and Linguistics · 2 worksSafety Research · 1 workSocial Sciences · 1 work

🧭 Topics 4Research subjects and languages the work is about.Evaluation & benchmarks · 1 workBias, fairness & safety · 1 workEfficient models & compression · 1 workLanguage models & pretraining · 1 work

 Works by year

2020s

20261 paper20241 paper

 Papers

The most cited first (OpenAlex and our library).

  1. RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors (2024 · 110 citations)
    Vendors and researchers often claim near-perfect accuracy for detecting AI-written text. These claims are rarely checked on common data, and existing benchmarks are too easy: they seldom vary decoding settings or include adversarial manipulation. The authors address this with RAID, a benchmark of about 6.2 million…
  2. Bias Dynamics in BabyLMs: Towards a Compute-Efficient Sandbox for Democratising Pre-Training Debiasing (2026)
    Studying how to prevent bias in language models during pre-training is rarely attempted, because retraining even a BERT-style model from scratch costs more than 500 GPU-hours.

 Co-authors here

7 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 65 times (of the 149,439 papers whose bibliographies we read); 17 citing papers with a page here →.

Updated

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