Characterize generalization beyond digit and binary predicates
Investigate whether inadvertent context-leakage attacks and measurements generalize to predicate types, language models, and deployment configurations beyond the digit-value and binary-attribute settings evaluated in the paper.
References
We leave generalization to other predicate types, models, and deployment configurations open.
— Inadvertent Context Leakage in Language Models
(2608.19857 - Fairoze et al., 20 Aug 2026) in Section 6, paragraph “Limitations.”
We treat this result as exploratory, with model-class invariance unresolved.
— Selection, Recombination, or a Fresh Solve? A Candidate-Free Control for Single-Pass Test-Time Aggregation
(2608.18379 - Farmanfarmaian, 18 Aug 2026) in Appendix G, “The reasoning-trained variant”; Section 5, Limitations