Pith. sign in

REVIEW 6 cited by

How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settings

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.11853 v3 pith:WUYAQV3T submitted 2023-05-19 cs.CL

Shuaichen Chang , Eric Fosler-Lussier This is my paper · ORCID
classification cs.CL
keywords promptllmstext-to-sqlconstructionsfutureresearchsettingsstrategies
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large language models (LLMs) with in-context learning have demonstrated remarkable capability in the text-to-SQL task. Previous research has prompted LLMs with various demonstration-retrieval strategies and intermediate reasoning steps to enhance the performance of LLMs. However, those works often employ varied strategies when constructing the prompt text for text-to-SQL inputs, such as databases and demonstration examples. This leads to a lack of comparability in both the prompt constructions and their primary contributions. Furthermore, selecting an effective prompt construction has emerged as a persistent problem for future research. To address this limitation, we comprehensively investigate the impact of prompt constructions across various settings and provide insights into prompt constructions for future text-to-SQL studies.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. ABISS: Evaluating Text-to-SQL Systems Through Agent Interaction

    cs.DB 2026-07 conditional novelty 6.0 of 10

    A new benchmark shows that text-to-SQL models detect problematic questions but fail to pinpoint the exact problem type and to resolve the question after a useful clarification.

  2. Knowledge Base Construction for Knowledge-Augmented Text-to-SQL

    cs.CL 2025-05 conditional novelty 6.0 of 10

    KAT-SQL constructs a reusable knowledge base for text-to-SQL by expanding training data with LLM-generated knowledge and retrieving/refining the best entries for each query.

  3. DCG-SQL: Enhancing In-Context Learning for Text-to-SQL with Deep Contextual Schema Link Graph

    cs.AI 2025-05 conditional novelty 6.0 of 10

    DCG-SQL retrieves text-to-SQL demonstrations by embedding a question-to-schema link graph, improving execution accuracy on Spider by up to about 10 points over random demonstrations on small LLMs.

  4. Are Human Interactions Replicable by Generative Agents? A Case Study on Pronoun Usage in Hierarchical Interactions

    cs.CL 2025-01 conditional novelty 6.0 of 10

    In a leader/subordinate discussion simulation, most LLM agents do not reproduce the human pronoun pattern, and knowing the pattern does not help them show it.

  5. What Really Matters for Table LLMs? A Meta-Evaluation of Model and Data Effects

    cs.CL 2025-01 conditional novelty 6.0 of 10

    By independently varying base models and training data across 12 models, this study shows that base model choice influences out-of-domain table task performance more than the instruction-tuning dataset does.

  6. Rethinking Table Instruction Tuning

    cs.CL 2025-01 conditional novelty 5.0 of 10

    A systematic hyperparameter study of table instruction tuning finds that small learning rates and 2,600 examples suffice, yielding TAMA, an 8B model competitive with GPT-3.5/GPT-4 on table benchmarks while keeping gen...

Pith tools