RIFT

A study applying the RIFT global rubric failure taxonomy to two clinical benchmarks found that an LLM judge flagged 29.6% of HealthBench Professional criteria as non-atomic and 65.4% as misaligned or …

Researchers compared six offline reinforcement-learning methods for distilling reasoning from large language models into smaller ones, finding that SFT, RFT, and RIFT produce nearly identical weight u…