{
  "id": 4500,
  "url": "https://arxiv.org/abs/2605.11632v2",
  "title": "Macro: Enhancing Multilingual Counterfactual Explanations through Alignment-as-Preference Optimization",
  "summary": "Self-generated counterfactual explanations (SCEs) are minimally modified inputs (minimality) generated by large language models (LLMs) that flip their own predictions (validity), offering a causally grounded approach to unraveling black-box LLM behavior. Yet extending them beyond English remains challenging: existing methods struggle to produce valid SCEs in non-dominant languages, and a persistent trade-off between validity and minimality undermines explanation quality. We introduce Macro, a pr",
  "authors": "Yilong Wang, Qianli Wang, Bohao Chu, Yihong Liu, Jing Yang, Simon Ostermann",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-12T06:56:18.000Z",
  "fetched_at": "2026-07-14T16:31:03.578Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4500",
  "original_url": "https://arxiv.org/abs/2605.11632v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}