Circuits of LLM Classifierswith Sajani Vithana, Kunal Talreja, Haewon Jeong, Viveck R. Cadambe +11 versionW_3xsqnymhv1 · current
Circuits of LLM ClassifiersHadi Khalaf, Sajani Vithana, Kunal Talreja et al.0 citations2610.30076v12026arXivon Valency
Robust AI Evaluation through Maximal LotteriesHadi Khalaf, Serena L. Wang, Daniel Halpern et al.0 citations2602.21297v12026arXiv
Inference-Time Reward Hacking in Large Language ModelsHadi Khalaf, Claudio Mayrink Verdun, Alex Oesterling et al.2 citations2506.19248v22025arXiv
AI Alignment at Your DiscretionMaarten Buyl, Hadi Khalaf, Claudio Mayrink Verdun et al.8 citations2502.10441v12025arXiv