Preprint
Oct 2026
LIFT: Scoped Constraints for Evaluating and Training Instruction Following
Common instruction following (IF) benchmarks, such as IFEval, evaluate the ability of language models (LMs) to follow simple constraints that can easily be verified programmatically. These same constraints, in turn, are used as reward signals for reinforcement learning. This design may lead to reward hacking of constra...
Eran Goldstein, Yuval Belfer, Yonatan Belinkov et al.
· 0 citations