SOURCE-LINKED INTELLIGENCE

Evidence-Aligned Local Composition of Discrete Experts for Sequence Restoration

arXiv · AI, language, vision and robotics · article · Sep 5, 2026 · UTC

A document modeled as a discrete sequence of tokens can be thought of as being generated from a composition of texts from different domains; a README file, for example, moves between prose, code, and configuration. When such a document is corrupted and only frozen domain experts are available, restoring it requires deciding both what is missing and which expert to trust at each position, at test time and without region labels or a trained router. We introduce evidence-aligned local composition, which infers a soft, position-wise weighting over the experts from the marginal evidence of the corr

Read original source ↗ Open in workspace

recordType

paper

region

Global