4 papers
Position: Capability Control Should be a Separate Goal From Alignment
Shoaib Ahmed Siddiqui, Eleni Triantafillou, David Krueger +1
Foundation models are trained on broad data distributions, yielding generalist capabilities that enable many downstream applications but also expand the space of potential misuse a…
Neural Mutual Information Estimation with Vector Copulas
Yanzhi Chen, Zijing Ou, Adrian Weller +1
Estimating mutual information (MI) is a fundamental task in data science and machine learning. Existing estimators mainly rely on either highly flexible models (e.g., neural networ…
From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization
Shoaib Ahmed Siddiqui, Adrian Weller, David Krueger +3
Recent unlearning methods for LLMs are vulnerable to relearning attacks: knowledge believed-to-be-unlearned re-emerges by fine-tuning on a small set of (even seemingly-unrelated) e…
On Evaluating LLMs' Capabilities as Functional Approximators: A Bayesian Perspective
Shoaib Ahmed Siddiqui, Yanzhi Chen, Juyeon Heo +2
Recent works have successfully applied Large Language Models (LLMs) to function modeling tasks. However, the reasons behind this success remain unclear. In this work, we propose a…