{
  "id": 4757564,
  "title": "Evaluating LLMs on Conversational Text-to-SQL under Chain Ambiguity and Intent Drift",
  "url": "https://urgent.news/2026/08/30/evaluating-llms-on-conversational-text-to-sql-under-chain-ambiguity",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-30T04:24:08.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2608.29543v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Recent advances in large language models (LLMs) have established conversational text-to-SQL as a practical interface between users and databases, often involving multiple turns of clarification and revision. However, existing benchmarks primarily evaluate execution accuracy, leaving the unfolding and shifting of user intent across turns largely uncovered. To address this, we introduce TIDE-Bench,…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}