Recall Isn't Enough: Bounding Commitments in Personalized Language Systems
1d ago
Quick Take
The study introduces CBEA and LCV to enhance commitment handling in personalized language systems.
Key Points
- CBEA uses bounded evidence for better personalization.
- LCV validates commitments before generating responses.
- Achieves zero failures with lower input payload.
📖 Reader Mode
~2 min readAbstract: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 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yichi Zhang [view email]
[v1]
Fri, 15 May 2026 23:50:15 UTC (40 KB)
— Originally published at arxiv.org
More from arXiv cs.AI
See more →1d ago
FeaturedOriginal
From Prompts to Protocols: An AI Agent for Laboratory Automation
AI Summary
An AI agent integrates large language models for automating laboratory protocols, enhancing efficiency and accuracy.