PPaperPicks

Gjergji Kasneci

Technical University of Munich, Germany

18 papers at tracked venues · 12 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0002-3123-7268 ↗Google Scholar ↗Homepage ↗

Venues

ACL ×5EMNLP ×5ICML ×4AAAI ×2ECAI ×1SIGKDD ×1

Frequent coauthors

Bardh Prenkaj
×11
Shuo Yang
×8
Zheyu Zhang
×5
Chenchen Yuan
×3
Tobias Leemann
×3
Alina Fastowski
×2
Efstratios Zaradoukas
×2
Felix Steinbauer
×2
Yuxiao Li
×1
Aysenur Kocak
×1
Roman Abramov
×1
Michael Kirchhof
×1

Papers

  1. Analysing the Safety Pitfalls of Steering Vectors
    ACL 2026 ·
    Yuxiao Li
    ,
    Alina Fastowski
    ,
    Efstratios Zaradoukas
    ,
    Bardh Prenkaj
    , Gjergji Kasneci
  2. SAGE: Sparse Adaptive Guidance for Dependency-Aware Tabular Data Generation
    ACL 2026 ·
    Shuo Yang
    ,
    Zheyu Zhang
    ,
    Bardh Prenkaj
    , Gjergji Kasneci
  3. Where Paths Split: Localized, Calibrated Control of Moral Reasoning in Large Language Models
    ACL 2026 ·
    Chenchen Yuan
    ,
    Zheyu Zhang
    , Gjergji Kasneci
  4. CURE: Controlled Unlearning for Robust Embeddings - Mitigating Conceptual Shortcuts in Pre-Trained Language Models
    EMNLP 2025 ·
    Aysenur Kocak
    ,
    Shuo Yang
    ,
    Bardh Prenkaj
    , Gjergji Kasneci
  5. Doubling Your Data in Minutes: Ultra-fast Tabular Data Generation via LLM-Induced Dependency Graphs
    EMNLP 2025 ·
    Shuo Yang
    ,
    Zheyu Zhang
    ,
    Bardh Prenkaj
    , Gjergji Kasneci
  6. From Confidence to Collapse in LLM Factual Robustness
    EMNLP 2025 ·
    Alina Fastowski
    ,
    Bardh Prenkaj
    , Gjergji Kasneci
  7. Graph Inverse Style Transfer for Counterfactual Explainability
    ICML 2025 ·
    Bardh Prenkaj
    ,
    Efstratios Zaradoukas
    , Gjergji Kasneci
  8. Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers
    ICML 2025 ·
    Roman Abramov
    ,
    Felix Steinbauer
    , Gjergji Kasneci
  9. Not All Features Deserve Attention: Graph-Guided Dependency Learning for Tabular Data Generation with Language Models
    EMNLP 2025 ·
    Zheyu Zhang
    ,
    Shuo Yang
    ,
    Bardh Prenkaj
    , Gjergji Kasneci
  10. Position: Uncertainty Quantification Needs Reassessment for Large Language Model Agents
    ICML 2025 ·
    Michael Kirchhof
    , Gjergji Kasneci,
    Enkelejda Kasneci
  11. Probabilistic Aggregation and Targeted Embedding Optimization for Collective Moral Reasoning in Large Language Models
    ACL 2025 ·
    Chenchen Yuan
    ,
    Zheyu Zhang
    ,
    Shuo Yang
    ,
    Bardh Prenkaj
    , Gjergji Kasneci
  12. RAZOR: Sharpening Knowledge by Cutting Bias with Unsupervised Text Rewriting
    AAAI 2025 ·
    Shuo Yang
    ,
    Bardh Prenkaj
    , Gjergji Kasneci
  13. SCISSOR: Mitigating Semantic Bias through Cluster-Aware Siamese Networks for Robust Classification
    ICML 2025 ·
    Shuo Yang
    ,
    Bardh Prenkaj
    , Gjergji Kasneci
  14. Enhancing Fairness through Reweighting: A Path to Attain the Sufficiency Rule
    ECAI 2024 ·
    Xuan Zhao
    ,
    Klaus Broelemann
    ,
    Salvatore Ruggieri
    , Gjergji Kasneci
  15. I Prefer Not to Say: Protecting User Consent in Models with Optional Personal Data
    AAAI 2024 ·
    Tobias Leemann
    ,
    Martin Pawelczyk
    ,
    Christian Thomas Eberle
    , Gjergji Kasneci
  16. P-TA: Using Proximal Policy Optimization to Enhance Tabular Data Augmentation via Large Language Models
    ACL 2024 ·
    Shuo Yang
    ,
    Chenchen Yuan
    ,
    Yao Rong
    ,
    Felix Steinbauer
    , Gjergji Kasneci
  17. The Language of Trauma: Modeling Traumatic Event Descriptions Across Domains with Explainable AI
    EMNLP 2024 ·
    Miriam Schirmer
    ,
    Tobias Leemann
    , Gjergji Kasneci,
    Jürgen Pfeffer
    ,
    David Jurgens
  18. Unifying Evolution, Explanation, and Discernment: A Generative Approach for Dynamic Graph Counterfactuals
    SIGKDD 2024 ·
    Bardh Prenkaj
    ,
    Mario Villaizán-Vallelado
    ,
    Tobias Leemann
    , Gjergji Kasneci