Profiles2020-2026
Johannes Bjerva
Aalborg University Copenhagen
12Papers
6Last author
16Unique co-authors
1First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers12
- Do LLMs Really Memorize Personally Identifiable Information? Revisiting PII Leakage with a Cue-Controlled Memorization FrameworkAuthor 4 of 4ACL 2026 · 1 citation
- Follow the Path: Reasoning over Knowledge Graph Paths to Improve Large Language Model FactualityAuthor 2 of 3ACL Findings 2026
- When Topology Betrays Privacy: Lattice-Based Reconstruction Attacks on Secure Aggregation in Decentralized Federated LearningAuthor 3 of 5CCS 2026
- Against All Odds: Overcoming Typology, Script, and Language Confusion in Multilingual Embedding Inversion AttacksAuthor 4 of 4AAAI 2025 · 9 citations
- How Do Hackathons Foster Creativity? Towards Automated Evaluation of Creativity at ScaleAuthor 6 of 7CHI 2025 · 4 citations
- Shared Path: Unraveling Memorization in Multilingual LLMs through Language SimilaritiesAuthor 3 of 4EMNLP 2025 · 1 citation
- ALGEN: Few-shot Inversion Attacks on Textual Embeddings via Cross-Model Alignment and GenerationAuthor 3 of 3ACL 2025
- Text Embedding Inversion Security for Multilingual Language ModelsAuthor 3 of 3ACL 2024 · 10 citations
- What is "Typological Diversity" in NLP?Author 4 of 4EMNLP 2024 · 2 citations
- The Past, Present, and Future of Typological Databases in NLPAuthor 3 of 3EMNLP Findings 2023 · 2 citations
- Zero-Shot Cross-Lingual Transfer with Meta LearningAuthor 3 of 4EMNLP 2020 · 12 citations
- SubjQA: A Dataset for Subjectivity and Review ComprehensionAuthor 1 of 5EMNLP 2020
