{
  "id": 3890,
  "url": "https://arxiv.org/abs/2606.13693v1",
  "title": "Limited Marginal Benefit of Reasoning-Heavy LLM Deployment in ESG Narrative Scoring: A 4-Model Consensus Study on Japanese Listed Firms",
  "summary": "Automated scoring of ESG narrative disclosures with large language models (LLMs) is gaining traction, yet whether reasoning-heavy frontier models add value commensurate with their cost remains empirically unsettled. We evaluate this question on a corpus of ten Japanese listed firms across three rubric axes -- quantitative targets, progress-tracking infrastructure, and external-standard alignment -- using a four-model consensus design that combines a reasoning-on frontier model with three reasoni",
  "authors": "Hiroyuki Kokubu",
  "category": "research",
  "topics": "safety-alignment,privacy-surveillance",
  "orgs": null,
  "regions": "japan",
  "published_at": "2026-05-22T03:35:33.000Z",
  "fetched_at": "2026-07-14T16:30:36.740Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/3890",
  "original_url": "https://arxiv.org/abs/2606.13693v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}