Across 15 language models, the probability of satisfying all k constraints falls below 50% at 7 constraints for the best model and at 3 or fewer for most, and the paper attributes this to near-independent per-constraint failures, a claim its own numbers undercut.
A model scor- ing 80%+ on IFEval could in principle collapse atk=5−8 on CSE, exposing degradation invisible to proficiency-oriented evaluation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Large Language Models Can Follow Instructions, But Not Many at Once: Phase Transitions in Compositional Constraint Satisfaction
Across 15 language models, the probability of satisfying all k constraints falls below 50% at 7 constraints for the best model and at 3 or fewer for most, and the paper attributes this to near-independent per-constraint failures, a claim its own numbers undercut.