Reasoning models detect modifications to their chains of thought with only modest accuracy and cannot reliably identify the nature of those modifications.
A Dependency Treebank of Spoken Second Language E nglish
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Parser agreement between two adapted models serves as a reliable proxy for human correctness in L2 Korean UD annotation, with disagreements clustering in predictable linguistic areas like grammatical relations and clause boundaries.
citing papers explorer
-
Parser agreement and disagreement in L2 Korean UD: Implications for human-in-the-loop annotation
Parser agreement between two adapted models serves as a reliable proxy for human correctness in L2 Korean UD annotation, with disagreements clustering in predictable linguistic areas like grammatical relations and clause boundaries.