English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL (Jun 2024, arXiv)

Forum topic · 小凯 · 2026-07-05

Summary

This post summarizes the June 2024 arXiv survey 'Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL' (arXiv:2406.08426) by Zijin Hong, Zheng Yuan, Qinggang Zhang, Hao Chen, Junnan Dong, Feiran Huang and colleagues. The survey systematically reviews how large language models are transforming natural-language access to structured databases, covering prompting strategies, fine-tuning approaches, retrieval-augmented and agentic pipelines, benchmark datasets, and evaluation protocols. The forum post situates the work within the broader evolution of neural information retrieval—from BM25 and dense retrieval to generative IR and agentic search—and highlights key open problems: benchmark consistency, hallucination, evaluation reliability, latency and cost, multilingual and multimodal extension, and safe deployment on private enterprise data. It also includes practical engineering checklists for data privacy, p99 latency budgets, quality auditing, and cost control, plus cross-references to related Text-to-SQL surveys and database function-calling work. A useful entry point for researchers and engineers building LLM-powered database interfaces.

Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL (Jun 2024, arXiv)

Metadata

| Field | Content | |---|---| | Title | Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL | | Authors / Affiliations | Zijin Hong, Zheng Yuan, Qinggang Zhang, Hao Chen, Junnan Dong, Feiran Huang, et al. (7 authors) | | Published | June 2024 | | Source | https://arxiv.org/abs/2406.08426 | | Type | Survey | | Section | Querying Structured Information |

One-line Summary

This survey systematically organizes LLM-based Text-to-SQL research, mapping how large language models are reshaping next-generation database interfaces.

Background and Motivation

At-scale search, recommendation, and personalization systems have long struggled with efficiency, scalability, and user-intent understanding. Traditional pipelines separate retrieval, ranking, and generation, which makes it hard to meet LLM-era demands for natural-language interaction, multi-hop reasoning, and up-to-date knowledge. This survey addresses that gap for the Text-to-SQL domain: translating natural-language questions into SQL over structured databases. Core scenarios include open-domain information access, enterprise knowledge retrieval, conversational search, and end-to-end architectures that couple external knowledge sources with generative models.

Core Contributions

  • Provides a unified perspective that organizes scattered Text-to-SQL work into a comparable framework.
  • Decomposes method components (schema representation, retrieval, re-ranking, planning, generation, feedback) for engineering practice.
  • Offers reproducible benchmarks, datasets, and taxonomy tables, lowering the entry cost for new researchers.
  • Discusses interfaces with LLM tool calling, reinforcement learning, and multi-agent collaboration, and paths from research prototypes to industrial systems.
  • Lists open problems: evaluation trustworthiness, latency and cost, hallucination and safety, cross-lingual and multimodal extension.
  • Taxonomy of Approaches

    | Dimension | Sub-categories | Representative ideas | Strengths | Limitations | |---|---|---|---|---| | Modeling paradigm | Discriminative / generative retrieval | Dual-tower, cross-encoder, DSI, GPT-indexed | Mature, scalable | Semantic drift, update cost | | LLM integration | RAG / Agent / Tool-use | Retrieval-augmented, search agents, API calls | Flexible, interpretable | Latency, error propagation | | Optimization goals | Relevance / diversity / freshness | Multi-objective LTR, RLHF, online learning | Business-aligned | Scarce annotations | | Evaluation | Offline / online / human | nDCG, MRR, LLM-as-judge, A/B tests | Comparable | Diverges from real satisfaction |

    The field generally juxtaposes four main lines: dense retrieval (high recall, low latency, first-stage), late interaction such as ColBERT (higher accuracy, larger indexes), generative IR (directly generating docids, simplifying cascades), and agentic search (sequential decision-making with multi-hop and self-reflection).

    Timeline of Research Evolution

  • 2019–2021: BERT re-ranking and DPR establish neural retrieval foundations.
  • 2022–2023: RAG and FreshLLMs drive retrieval-generation fusion.
  • 2024: Conversational/agentic search and Gen-RecSys take off.
  • 2025–2026: RL-trained search agents, Deep Research, and GraphRAG become new growth fronts.
  • Evaluation Paradigms

    Typical benchmarks and trends covered:

  • Datasets: MS MARCO, BEIR, Natural Questions, domain corpora, public recommendation sets; for Text-to-SQL, Spider and BIRD-style benchmarks.
  • Metrics: nDCG@10, MRR, Recall@k, Hit@k, human preference, task success rate, latency, token cost.
  • Baselines: BM25, dense retrieval, cross-encoder re-ranking, retrieval-free LLMs, commercial search APIs.
  • Ablations: contributions of retrieval steps, re-ranking depth, and training data scale.
  • Quantitative results should be checked against the original PDF tables.

    Key Takeaways

    1. Architecture: cascaded retrieve → re-rank → generate remains mainstream, but agentic paradigms make retrieval policy itself learnable. 2. Data: high-quality instruction data and click/session logs matter equally; synthetic data risks leakage and distribution shift. 3. Evaluation: the gap between offline metrics and online satisfaction is widening; LLM-as-judge needs human cross-validation. 4. Product: latency, cost, explainability, and safety are hard industrial constraints—not just academic benchmarks.

    Open Problems and Future Directions

    The authors highlight insufficient unified benchmarks, non-reproducible private data, LLM evaluation bias, and the safety/cost constraints of agentic systems. Future work includes finer-grained process supervision, joint retrieval-reasoning training, enterprise metadata governance, and multilingual/multimodal consistency.

    Engineering Checklist

    | Item | Question | Recommendation | |---|---|---| | Data | PII in training/index? Version control? | Partitioned indexes, anonymization, rollback-capable embeddings | | Latency | p99 budget? Retrieval steps? | Cascade + early stop, hot-query caching, async re-ranking | | Quality | Do offline gains translate online? | Interleaving experiments, human audits, citation checks | | Safety | Poisoning/bias from open retrieval? | Source whitelists, adversarial detection, output filtering | | Cost | Per-query token/GPU usage? | Small-model routing, distillation, hybrid sparse-dense |

    Related Entries

  • A Survey of Text-to-SQL in the Era of LLMs
  • A Survey on Employing Large Language Models for Text-to-SQL Tasks
  • Large language model for table processing: a survey, Jan 2025
  • Querying Databases with Function Calling, Jan 2025
  • References

  • Original: *Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL*, June 2024, arXiv: https://arxiv.org/abs/2406.08426

Tags

#text-to-sql#llm#survey#database-interfaces#retrieval-augmented-generation#agentic-search#nlp#arxiv

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208814