PPaperPicks

Pieter Delobelle

6 papers at tracked venues · 3 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Audit Me If You Can: Query-Efficient Active Fairness Auditing of Black-Box LLMs
  2. ProbLog4Fairness: A Neurosymbolic Approach to Modeling and Mitigating Bias
  3. SHADES: Towards a Multilingual Assessment of Stereotypes in Large Language Models
  4. BPE-knockout: Pruning Pre-existing BPE Tokenisers with Backwards-compatible Morphological Semi-supervision
  5. Metrics for What, Metrics for Whom: Assessing Actionability of Bias Evaluation Metrics in NLP
    EMNLP 2024 · Pieter Delobelle
  6. Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models