{
  "id": 7244237,
  "title": "MAxBench: A Multinomial Concept Recovery Benchmark",
  "url": "https://urgent.news/2026/09/11/maxbench-a-multinomial-concept-recovery-benchmark",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-11T17:08:57.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.13072v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "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…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}