research
The Model Learns When Another Check Cannot Change the Decision
DIVA prices evidence by its expected decision value and stops when no remaining check is worth its cost.
Summary
DIVA prices evidence by its expected decision value and stops when no remaining check is worth its cost.
Language models often request information that cannot alter the decision or continue after the evidence is sufficient. DIVA asks the model for a compact numeric decision model, imagines how each check could move the probability of a bad outcome and subtracts the check's cost. Its uncertainty-aware variant had lower regret than every tested model baseline across four domains and 20 models; in synthetic scenarios with known check reliability, DIVA cut the best baseline's regret by 75 percent. The method depends on estimates supplied by the model and the evaluated decision setup. It does not make those probabilities true, but it gives information seeking an explicit stopping rule tied to consequence rather than curiosity.
Why it matters
DIVA prices evidence by its expected decision value and stops when no remaining check is worth its cost.
Limits and context
- Language models often request information that cannot alter the decision or continue after the evidence is sufficient.
- It does not make those probabilities true, but it gives information seeking an explicit stopping rule tied to consequence rather than curiosity.
Key claims
DIVA prices evidence by its expected decision value and stops when no remaining check is worth its cost.
Qualification: Language models often request information that cannot alter the decision or continue after the evidence is sufficient.
Evidence: source-2026-10-26-010
Sources
- arXiv preprint 2610.32181, original v1arXiv · primary research
Corrections
No corrections have been recorded for this story.