English

Recall Isn't Enough: Bounding Commitments in Personalized Language Systems

Artificial Intelligence 2026-05-20 v2 Computation and Language Human-Computer Interaction

Abstract

Long-context and memory systems usually treat personalization as a recall problem. In practice, many failures occur later, when a system commits: it turns noisy hints into hard constraints, drops rare witnesses, forgets downstream obligations, or answers despite infeasibility. We introduce Contract-Bounded Evidence Activation (CBEA) with Lexicographic Commitment Validation (LCV). CBEA activates a bounded evidence set using typed coverage, tail witnesses, and consequence debt; LCV validates structured commitments before prose and routes infeasible states to repair, abstention, or recontract. Across 360 fixtures and three generation backends, CBEA+LCV reaches zero failures within validator scope at 0.49-0.60 availability over attempted runs. Raw and long-context baselines with the same LCV gate reach zero only at 0.003-0.092. A shadow oracle diagnostic marks the limit: CBEA+LCV recalls 0.012 of uncompiled visible facts, while raw recalls 0.53. The result is a bounded operating point: explicit commitment control and 74-75% lower median input payload, not universal memory dominance.

Cite

@article{arxiv.2605.16712,
  title  = {Recall Isn't Enough: Bounding Commitments in Personalized Language Systems},
  author = {Rui Tang and Yichi Zhang and Xi Chen and Chen Dong and Youwei Yang and Yumeng Shen and Qiangqiang Liu},
  journal= {arXiv preprint arXiv:2605.16712},
  year   = {2026}
}

Comments

14 pages, 3 figures, 22 tables; preprint version