Jan Wehner

13 papers A* 1B 2Journal 8Unranked 2
YearRankTypeTitle / Venue / Authors
2025 J jnl
Probe-based Fine-tuning for Reducing Toxicity.
CoRR
Jan Wehner, Mario Fritz
2025 J jnl
Safety is Essential for Responsible Open-Ended Systems.
CoRR
Ivaxi Sheth, Jan Wehner, Sahar Abdelnabi, Ruta Binkyte, Mario Fritz
2025 J jnl
Taxonomy, Opportunities, and Challenges of Representation Engineering for Large Language Models.
CoRR
Jan Wehner, Sahar Abdelnabi, Daniel Tan, David Krueger, Mario Fritz
2025 J jnl
Taxonomy, Opportunities, and Challenges of Representation Engineering for Large Language Models.
Trans. Mach. Learn. Res.
Jan Wehner, Sahar Abdelnabi, Daniel Tan, David Krueger, Mario Fritz
2024 — conf
Explaining Learned Reward Functions with Counterfactual Trajectories.
AIEB@ECAI
Jan Wehner, Frans A. Oliehoek, Luciano Cavalcante Siebert
2024 J jnl
Explaining Learned Reward Functions with Counterfactual Trajectories.
CoRR
Jan Wehner, Frans A. Oliehoek, Luciano Cavalcante Siebert
2024 — conf
Immunization against harmful fine-tuning attacks.
EMNLP (Findings)
Domenic Rosati, Jan Wehner, Kai Williams, Lukasz Bartoszcze, Hassan Sajjad, Frank Rudzicz
2024 J jnl
Immunization against harmful fine-tuning attacks.
CoRR
Domenic Rosati, Jan Wehner, Kai Williams, Lukasz Bartoszcze, Jan Batzner, Hassan Sajjad, Frank Rudzicz
2024 A* conf
Representation Noising: A Defence Mechanism Against Harmful Finetuning.
NeurIPS
Domenic Rosati, Jan Wehner, Kai Williams, Lukasz Bartoszcze, Robie Gonzales, Carsten Maple, Subhabrata Majumdar, Hassan Sajjad, Frank Rudzicz
2024 J jnl
Representation noising effectively prevents harmful fine-tuning on LLMs.
CoRR
Domenic Rosati, Jan Wehner, Kai Williams, Lukasz Bartoszcze, David Atanasov, Robie Gonzales, Subhabrata Majumdar, Carsten Maple, Hassan Sajjad, Frank Rudzicz
2023 J jnl
On robust vs fast solving of qualitative constraints.
J. Heuristics
Jan Wehner, Michael Sioutis, Diedrich Wolter
2021 B conf
On Robust Vs Fast Solving of Qualitative Constraints.
ICTAI
Jan Wehner, Michael Sioutis, Diedrich Wolter
2012 B conf
T.F.O.: tangible flying objects.
TEI
Rinat Mustafin, Jan Wehner, Wolfgang Sattler, Kristian Gohlke