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

Computer Science > Artificial Intelligence [Submitted on 15 May 2026] Recall Isn't Enough: Bounding Commitments in Personalized Language Systems Rui Tang, Yichi Zhang, Xi Chen, Chen Dong, Youwei Yang, Yumeng Shen 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. Comments: 14 pages, 3 figures, 22 tables; preprint version Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Human-Computer Interaction (cs.HC) ACM classes: I.2.7; H.3.3 Cite as: arXiv:2605.16712 [cs.AI]   (or arXiv:2605.16712v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2605.16712 Focus to learn more Submission history From: Yichi Zhang [view email] [v1] Fri, 15 May 2026 23:50:15 UTC (40 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-05 Change to browse by: cs cs.CL cs.HC References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)