{
  "id": 4652,
  "url": "https://arxiv.org/abs/2605.09129v1",
  "title": "Data-driven Circuit Discovery for Interpretability of Language Models",
  "summary": "Circuit discovery aims to explain how language models (LMs) implement a specific task by localizing and interpreting a circuit, a computational subgraph responsible for the LM's behavior. Existing circuit discovery methods are hypothesis-driven; they first informally define a task with a dataset, and then apply a circuit discovery algorithm over that dataset to obtain a single circuit. This imposes two strong assumptions: that the LM implements the task with a single circuit, and that the datase",
  "authors": "Daking Rai, Mor Geva, Ziyu Yao",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-09T19:20:57.000Z",
  "fetched_at": "2026-07-14T16:31:08.357Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4652",
  "original_url": "https://arxiv.org/abs/2605.09129v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}