Controlled Acquisition and Abstention in Three-Channel Score Conflicts

2026-10-07

AI Summary

This study addresses the decision-making challenge of balancing the cost of acquiring additional modalities against the option to abstain when multimodal information conflicts. To this end, it constructs a three-score benchmark and proposes a threshold strategy based on mechanism-specific reward models. This strategy dynamically determines whether to pay for a third score or abstain after observing two scores, enabling precise routing decisions by distinguishing ambiguity types. The work reveals a decoupling between selection value and full-modality accuracy under budget constraints. Experimental results demonstrate that the proposed threshold strategy matches full-request accuracy with fewer queries, significantly outperforming majority voting baselines in utility under specific budgets.

Abstract

When audio, video, and text disagree, accuracy alone does not show whether to acquire another source or abstain. We study these choices in a controlled three-score benchmark: a policy observes two signed scores, may request the third at a cost, and can abstain. The primary reward is mechanism-specific: abstention is correct only for one designated ambiguity mechanism and is penalized under mixed corruption. Matched controls show that a threshold policy matches always-request decisions with fewer requests; its advantage over always-answer fusion depends on the reward assigned to that ambiguity. On a partially held-out synthetic split, the threshold policy reaches 0.789 +/- 0.006 targeted decision accuracy and 0.481 +/- 0.014 utility across 83 seeds. A three-score majority reference reaches 0.626 +/- 0.008 and 0.252 +/- 0.016, but uses more information. In a matched-budget test, a train-only value selector improves utility over no-query and matched-random policies at 10% and 25% budgets, while pair uncertainty has higher utility at every budget. At 50% and 63.7% budgets, the selector lowers utility despite slightly higher non-ambiguous accuracy. If all abstentions are scored incorrect, majority outranks the threshold policy in utility. At a central temporal setting, full-trace controls match the neural models while position perturbations separate them. On held-out-actor emotion clips, eight-frame fusion has opposite-signed accuracy differences for two encoder pairs, with both actor intervals containing zero; matched-request routing gains are small and uncertain. These results separate full-modality accuracy from pre-request selection value and show that selection value depends on budget and the observed-pair ranking.

Problem

• multimodal conflict
• selective acquisition
• abstention
• three-channel scoring
• budget-constrained decision

Innovation

• three-channel score conflicts
• threshold policy
• controlled acquisition and abstention
• budget-constrained value selection
• pair uncertainty