Extend forget-prompt discovery beyond retained-data structure
Extend Targeted Active Search beyond settings in which retained prompts provide sufficient coverage of the entities and prompt structures surrounding the forgotten target, for example by generating candidate entities and prompt structures from external knowledge or through adaptive language-model-based exploration.
References
Extending target discovery beyond this setting, for example, by generating candidate entities and prompt structures from external knowledge or through adaptive language-model-based exploration, is an important direction for future work.
— Extracting Forgotten Prompts from Targeted Unlearned Models
(2609.03662 - Hoi-Ting et al., 3 Sep 2026) in Section 6, “Discussion,” paragraph “Scope and limitations”
In this example, entity expansion could place a complete cut within a ten-turn pool; its effectiveness as a deletion strategy remains untested.
— MemCut: Every Secret Leaves a Trail in the Long-Term Memory of LLM Agents
(2610.21405 - Zhang et al., 15 Oct 2026) in Appendix D, Section “Following entities could reach a complete cut”