Signals 4 · free daily AI digest

Evaluating LLMs on Conversational Text-to-SQL under Chain Ambiguity and Intent Drift

Paper recorded by Signals 4 on 2026-08-30 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-08-30 on arXiv · recorded by Signals 4 on 2026-09-01

Category: cs.AI · 人工智能 · first seen 2026-09-01

Abstract

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,

Read on arXiv →

#277 most recent of 300 cs.AI papers we have recorded · ↑ newer: PhysWave: Physics-Guided Latent Diffusion Models for Controllable Spat · ↓ older: AGM: Achievement-Grounded Memory for Closed-Loop Agents with Frozen VL
Cite this page: Evaluating LLMs on Conversational Text-to-SQL under Chain Ambiguity and Intent Drift: the #277 most recent of 300 cs.AI papers we have recorded (as of 2026-08-30). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/evaluating-llms-on-conversational-text-to-sql-under-chain-ambiguity-and-intent-d.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.AI papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions