PPaperPicks

Filip Sondej

2 papers at tracked venues · 1 at CORE A* · active 2025–2025

Venues

Frequent coauthors

Yushi Yang
×1
Harry Mayne
×1
Andrew Lee
×1
Adam Mahdi
×1
Pierre Peigné
×1
Mikolaj Kniejski
×1
Matthieu David
×1
Jason Hoelscher-Obermaier
×1
Christian Schröder de Witt
×1
Esben Kran
×1

Papers

  1. How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis
    EMNLP 2025 ·
    Yushi Yang
    , Filip Sondej,
    Harry Mayne
    ,
    Andrew Lee
    ,
    Adam Mahdi
  2. Multi-Agent Security Tax: Trading Off Security and Collaboration Capabilities in Multi-Agent Systems
    AAAI 2025 ·
    Pierre Peigné
    ,
    Mikolaj Kniejski
    , Filip Sondej,
    Matthieu David
    ,
    Jason Hoelscher-Obermaier
    ,
    Christian Schröder de Witt
    ,
    Esben Kran