LIFT: Scoped Constraints for Evaluating and Training Instruction Following
Read the original on arXiv Computation and Language →LIFT introduces Lift-Bench, a new instruction‑following benchmark that asks language models to draft a document based on a topic and a structured outline, with constraints scoped to specific sections for finer control. The benchmark includes both verifiable and judged constraints and a training counterpart, Lift‑Train, designed to reduce reward hacking by providing both main‑task and instruction‑following constraints. Experiments show that state‑of‑the‑art models struggle with the harder subsets, and training on Lift‑Train is less prone to reward hacking than traditional IF training.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.