Scholar

Florent Draye

Google Scholar ID: _oARI30AAAAJ

PhD Student, MPI-IS

LLM Interpretability

Homepage↗Google Scholar↗

Citations & Impact

All-time

Citations

0

H-index

0

i10-index

0

Publications

1

Co-authors

0

Contact

No contact links provided.

Publications

7 items

How Does Alignment Tuning Shape Representations of Sycophancy and Related Cue-Induced Biases in LLMs?

2026

Cited

0

PruneGround: Plug-and-play Spatial Pruning for 3D Visual Grounding

2026

Cited

0

STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations

2026

Cited

0

CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution Graphs

2026

Cited

0

Identifying Intervenable and Interpretable Features via Orthogonality Regularization

2026

Cited

0

Sparse Attention Post-Training for Mechanistic Interpretability

2025

Cited

0

Tracing Multilingual Representations in LLMs with Cross-Layer Transcoders

2025

Cited

0

Resume (English only)

Co-authors

0 total

Co-authors: 0 (list not available)