On the Limits of Support-Preserving Alignment and Bounded Filtering
We study whether alignment schemes that reshape a base model's output distribution, combined with bounded safety filters, can drive the probability of harmful behavior to zero in modern large language models. Recent research suggests that harmful behaviors can persist under preference-based alignment and that external filtering can be computationally hard in the worst case, but it remains unclear whether practical alignment pipelines that largely preserve internal representations can eliminate harmful behavior entirely rather than merely suppressing its most visible forms. We formalize this setting using support-preserving alignment operators together with bounded filtering algorithms und...
| Authors | Aryan Dutt, Rui Mao, Anupam Chattopadhyay |
|---|---|
| Primary category | cs.LG |
| Published | 1 July 2026 |
| Last updated at source | 1 August 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.