{
  "id": 18757,
  "url": "https://arxiv.org/abs/2608.09900",
  "title": "Decoding-Level Taboo: A Diagnostic Stress Test for LLM Robustness",
  "summary": "Large language model evaluations typically focus on performance under nominal conditions, creating an illusion of capability where models comfortably walk a narrow, highly optimized generation corridor. In real-world deployments, however, complex system prompts, safety guardrails, and structural constraints continuously force models off this nominal path, driving a divergence between benchmark scores and deployment performance. To address this issue, we introduce Decoding-Level Taboo, a zero-pro",
  "authors": "Tadanobu Chuyo Kamijo, Ori Rottenstreich, Javier Conde, Gonzalo Martínez, Pedro Reviriego",
  "category": "research",
  "topics": "healthcare",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-09T20:00:00.000Z",
  "fetched_at": "2026-08-13T05:10:37.786Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/18757",
  "original_url": "https://arxiv.org/abs/2608.09900",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}