{
  "id": 4936,
  "url": "https://arxiv.org/abs/2605.04488v1",
  "title": "How Does Thinking Mode Change LLM Moral Judgments? A Controlled Instant-vs-Thinking Comparison Across Five Frontier Models",
  "summary": "We evaluate whether enabling provider-exposed reasoning mode changes moral judgments within the same model checkpoint. Across 100 moral-judgment scenarios and five frontier reasoning-trained LLMs (Claude Sonnet 4.6, GPT 5.5, Gemini 3 Flash, DeepSeek V3.1, and Qwen3.5 397B), aggregate binary-verdict agreement remains high and statistically indistinguishable between instant and thinking modes (Krippendorff's alpha = 0.78 vs. 0.79). However, disagreement is concentrated in 21 model-disputed scenari",
  "authors": "Sai Sourabh Madur",
  "category": "research",
  "topics": null,
  "orgs": "anthropic,google,deepseek",
  "regions": null,
  "published_at": "2026-05-06T04:33:04.000Z",
  "fetched_at": "2026-07-14T16:31:21.934Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4936",
  "original_url": "https://arxiv.org/abs/2605.04488v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}