@InProceedings{jang2026exploration,
	author = {Joschka Braun* and Eyon Jang* and Damon Falck* and Nathalie Kirch and Achu Menon and Perusha Moodley and Scott Emmons and Roland S. Zimmermann and David Lindner},
	title = {Exploration Hacking: Can LLMs Learn to Resist RL Training?},
	booktitle = {International Conference on Machine Learning (ICML)},
	year = {2026},
	url = {https://arxiv.org/abs/2604.28182},
	eprint = {2604.28182},
}

@InProceedings{braun2026beyond,
	author = {Joschka Braun and Carsten Eickhoff and Seyed Ali Bahrainian},
	title = {Beyond Multiple Choice: Evaluating Steering Vectors for Summarization},
	booktitle = {EACL 2026, Findings of the Association for Computational Linguistics},
	year = {2026},
	url = {https://aclanthology.org/2026.findings-eacl.200/},
}

@InProceedings{braun2025_resisting,
	author = {Joschka Braun* and Eyon Jang* and Damon Falck* and Roland S. Zimmermann and David Lindner and Scott Emmons},
	title = {Resisting RL Elicitation of Biosecurity Capabilities: Reasoning Models Exploration Hacking on WMDP},
	booktitle = {NeurIPS 2025 Workshop on Biosecurity Safeguards for Generative AI (Oral, Best Paper Runner-Up)},
	year = {2025},
	url = {https://openreview.net/forum?id=ZNZn43baQX},
	note = {Decision: Accept (Oral), Best Paper Runner-Up},
}

@InProceedings{braun2026understandingunreliabilitysteeringvectors,
	author = {Joschka Braun},
	title = {Understanding Unreliability of Steering Vectors in Language Models: Geometric Predictors and the Limits of Linear Approximations},
	booktitle = {MSc Thesis, University of Tübingen},
	year = {2026},
	url = {https://arxiv.org/abs/2602.17881},
	eprint = {2602.17881},
}

@InProceedings{braun2025beyond,
	author = {Joschka Braun and Carsten Eickhoff and Seyed Ali Bahrainian},
	title = {Beyond Multiple Choice: Evaluating Steering Vectors for Adaptive Free-Form Summarization},
	booktitle = {ICML 2025 Workshop on Reliable and Responsible Foundation Models},
	year = {2025},
	url = {https://openreview.net/forum?id=sbm53EmmGp},
	eprint = {2505.24859},
}

@InProceedings{braun2025understanding,
	author = {Joschka Braun and Carsten Eickhoff and David Krueger and Seyed Ali Bahrainian and Dmitrii Krasheninnikov},
	title = {Understanding (Un)Reliability of Steering Vectors in Language Models},
	booktitle = {ICLR 2025 Workshop on Foundation Models in the Wild},
	year = {2025},
	url = {https://openreview.net/forum?id=qGCp2AYosf},
	eprint = {2505.22637},
}

@InProceedings{Braun_Reweighting_Logits_2024,
	author = {Joschka Braun and Bálint Mucsányi and Seyed Ali Bahrainian},
	title = {Logit Reweighting for Topic-Focused Summarization},
	booktitle = {Implemented a custom LogitsProcessor class to reweight logits of topic-relevant tokens during summary generation. Evaluated and compared different strategies on the NEWTS dataset.},
	year = {2024},
	eprint = {2507.05235},
}

@InProceedings{Braun2022BSCTHESIS,
	author = {Joschka Braun},
	title = {Verbal Epistemic Uncertainty Estimation for Numeric Values with GPT-3},
	booktitle = {BSc Thesis at Univesity of Tübingen},
	year = {2022},
}

@misc{Brown2026ExplorationHackingDebate,
	author = {Jason Brown* and Nathalie Kirch* and Joschka Braun and Helen Yannakoudakis and Roland S. Zimmermann and David Lindner},
	title = {Exploration Hacking in AI Debate: Initial Empirics and Generalisation Splitting},
	booktitle = {LessWrong},
	year = {2026},
	month = {September},
	day = {8},
	url = {https://www.lesswrong.com/posts/xjwtNid2xjqSJWB7z/exploration-hacking-in-ai-debate-initial-empirics-and},
	note = {Jason Brown and Nathalie Kirch contributed equally.},
}

@misc{Brown2026ExplorationHackingFramework,
	author = {Jason Brown* and Nathalie Kirch* and Joschka Braun and Helen Yannakoudakis and Roland S. Zimmermann and David Lindner},
	title = {A Conceptual Framework for Reasoning about Exploration Hacking},
	booktitle = {LessWrong},
	year = {2026},
	month = {September},
	day = {8},
	url = {https://www.lesswrong.com/posts/am5w2t9LzJB4sRhKw/a-conceptual-framework-for-reasoning-about-exploration},
	note = {Jason Brown and Nathalie Kirch contributed equally.},
}

@InProceedings{Braun_Exploration_Hacking_Blog_Post_2026,
	author = {Joschka Braun and Damon Falck and Eyon Jang},
	title = {A Conceptual Framework for Exploration Hacking},
	booktitle = {We formalize and decompose exploration hacking, where models strategically alter their exploration to resist RL training, presenting a conceptual framework and open problems ahead of our upcoming empirical paper.},
	year = {2026},
}

@InProceedings{Braun_Exploration_Hacking_Blog_Post_2025,
	author = {Damon Falck and Joschka Braun and Eyon Jang},
	title = {Exploration hacking: can reasoning models subvert RL?},
	booktitle = {Exploration hacking, where models subvert their RL training by selectively under-exploring, could threaten both the development of beneficial capabilities and the effectiveness of safety training.},
	year = {2025},
}

@InProceedings{Braun_Anthropic_Hackathon_2025,
	author = {Joschka Braun and Damon Falck and Eyon Jang},
	title = {Anthropic Alignment Hackathon: Exploration Hacking},
	booktitle = {Participated in the June 2025 Anthropic Alignment Hackathon in San Francisco, co-developing an "Exploration Hacking" prototype over two days alongside Damon Falck and Eyon Jang.},
	year = {2025},
}

@misc{rein2025hcasthumancalibratedautonomysoftware,
	author = {David Rein al.},
	title = {HCAST: Human-Calibrated Autonomy Software Tasks},
	booktitle = {Acknowledged Contributor to HCAST benchmark: Contributed task feedback and set human performance baselines for ML Engineering tasks.},
	year = {2025},
	eprint = {2503.17354},
}

@InProceedings{Braun_Steering_Blog_Post_2024,
	author = {Joschka Braun and Dmitrii Krasheninnikov and Usman Anwar and Robert Kirk and Daniel Tan and David Krueger},
	title = {A Sober Look at Steering Vectors for LLMs},
	booktitle = {Blog post on the key challenges in controlling LLM behaviour with steering vectors. Published on The Alignment Forum.},
	year = {2024},
}