Ahmad Dawar Hakimi

LMU Munich, University of Copenhagen, Munich Center for Machine Learning

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Interpretability & Mechanistic Interp (1)Data Curation & Synthetic Data (1)Eval Frameworks & Benchmarks (1)Natural Language Processing (1)

Frequent co-authors

Isabelle Augenstein (2)Kaiwei Lei (1)Hinrich Schütze (1)Lea Hirlimann (1)

Papers (2)

Jun 17, 2026

2d ago·also B and, KU, Munich Center for Machine Learning

Output Vector Editing for Memorization Mitigation in Large Language Models

Output vector editing can suppress up to 87.9% of memorized sequences in large language models, significantly outperforming traditional neuron-level methods.

Ahmad Dawar Hakimi, Kaiwei Lei, Isabelle Augenstein +1

Interpretability & Mechanistic Interp

Apr 15, 2026

Apr 15, 2026·also KU, Munich Center for Machine Learning

Do We Still Need Humans in the Loop? Comparing Human and LLM Annotation in Active Learning for Hostility Detection

LLM-labeled data can match human-labeled data in aggregate performance for hostility detection, but be warned: the errors are systematically different, especially in nuanced cases.

Ahmad Dawar Hakimi, Lea Hirlimann, Isabelle Augenstein +1

Data Curation & Synthetic Data Eval Frameworks & Benchmarks Natural Language Processing

Search

Ahmad Dawar Hakimi

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)