CRGC models instructions as constraint graphs, identifies bridge constraints, and cuts violations by 39% on three datasets while preserving reasoning performance.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
COPAL reveals a 33.1% average error rate on composed-policy queries across nine LLM chatbots, showing that existing single-policy benchmarks miss common failures.
citing papers explorer
-
Bridging Auxiliary Constraints to Resolve Instruction Following in Large Reasoning Models
CRGC models instructions as constraint graphs, identifies bridge constraints, and cuts violations by 39% on three datasets while preserving reasoning performance.
-
Beyond Single-Policy: Evaluating Composed Organization-Specific Policy Alignment in LLM Chatbots
COPAL reveals a 33.1% average error rate on composed-policy queries across nine LLM chatbots, showing that existing single-policy benchmarks miss common failures.