AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

MAxBench: A Multinomial Concept Recovery Benchmark

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Fine-grained control of language model behaviors (e.g., steering) is among the more actionable outcomes of interpretability research. For binary concepts such as refusal, a single direction in activation space often suffices for steering. However, many concepts are not binary: Animals and Countries contain many subcategories, each with multiple instances. For these concepts, the search space over possible representation geometries is far larger than for binary concepts; it is thus not clear what geometries are most appropriate, nor what methods are most effective at recovering them. In this wo

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-20T16:41:15.630Z. This is not the publication date.