MAxBench: A Multinomial Concept Recovery Benchmark

Research on steering language models mostly deals with yes-or-no concepts such as refusal. MAxBench tests concepts with many categories, such as animals or countries. Across 10 methods, 6 concepts and 4 models, affine subspaces worked best, largely because of better offsets. No method beat plain prompting. Authors: Divya Appapogu, Freya Behrens, Yonatan Belinkov, Aaron Mueller Paper: https://arxiv.org/abs/2609.13072v1