#database-queries News & Analysis

4 articles tagged with #database-queries. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

4 articles

AINeutralarXiv – CS AI · 3d ago6/10

🧠

QO-Bench: Diagnosing Query-Operator-Preserving Retrieval over Typed Event Tuples

Researchers introduce QO-Bench, a diagnostic benchmark for evaluating retrieval-augmented generation (RAG) systems on structured database-style queries over text. The benchmark reveals that current RAG systems excel at finding relevant passages but fail to preserve typed values needed for query operators like joins and counting, identifying operator execution rather than retrieval as the core bottleneck.

AIBullisharXiv – CS AI · May 116/10

🧠

CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation

Researchers introduce CA-SQL, an advanced Text-to-SQL pipeline that dynamically allocates computational resources based on task complexity to improve LLM reasoning. The method achieves state-of-the-art performance on the BIRD benchmark's challenging tier using only GPT-4o-mini, outperforming larger models and demonstrating the efficiency gains possible through intelligent inference-time optimization.

🧠 GPT-4

AINeutralarXiv – CS AI · Mar 36/104

🧠

From Conversation to Query Execution: Benchmarking User and Tool Interactions for EHR Database Agents

Researchers introduced EHR-ChatQA, a new benchmark for testing AI agents that interact with Electronic Health Record databases through natural language queries. The benchmark reveals significant reliability gaps in current state-of-the-art LLMs, with success rates dropping substantially when consistency across multiple trials is required.

AINeutralarXiv – CS AI · Mar 35/103

🧠

AWARE-US: Preference-Aware Infeasibility Resolution in Tool-Calling Agents

Researchers developed AWARE-US, a system to improve AI agents' ability to handle failed database queries by intelligently relaxing the least important user constraints rather than simply returning 'no results'. The system uses three LLM-based methods to infer constraint importance from dialogue, achieving up to 56% accuracy in correct constraint relaxation.