mlsanityData to 7 Oct 2026

Semantically Aligned Question and Code Generation for Automated Insight Generation

arXiv 2405.01556 ↗First posted 21 Mar 2024cs.SE cs.AI cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

Automated insight generation is a common tactic for helping knowledge workers, such as data scientists, to quickly understand the potential value of new and unfamiliar data. Unfortunately, automated insights produced by large-language models can generate code that does not correctly correspond (or align) to the insight. In this paper, we leverage the semantic knowledge of large language models to generate targeted and insightful questions about data and the corresponding code to answer those questions. Then through an empirical study on data from Open-WikiTable, we show that embeddings can be effectively used for filtering out semantically unaligned pairs of question and code. Additionally, we found that generating questions and code together yields more diverse questions.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 9 of its 19 references that are in the map. First posted on arXiv 21 Mar 2024.

Builds on

9 of 19 references.

References · 9

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 890
  3. 2022Text and Code Embeddings by Contrastive Pre-Trainingcited by 358
  4. 2022Large Language Models Meet NL2Code: A Surveycited by 135
  5. 2021Jigsaw: Large Language Models meet Program Synthesiscited by 103
  6. 2019When Deep Learning Met Code Searchcited by 45
  7. 2022Automatic Generation of Socratic Subquestions for Teaching Math Word Problemscited by 42
  8. 2023Open-WikiTable: Dataset for Open Domain Question Answering with Complex Reasoning over Tablecited by 40
  9. 2021Lux: Always-on Visualization Recommendations for Exploratory Dataframe Workflowscited by 10

Built on by

Cited by year

Citing papers per year: 2025: 3.

3 papers.

  1. 2025Diffusion is a code repair operator and generatorcited by 3
  2. 2025MDSF: Context-Aware Multi-Dimensional Data Storytelling Framework based on Large language Modelcited by 1
  3. 2025Tabularis Formatus: Predictive Formatting for Tablescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Leveraging Large Language Models to Generate Course-specific Semantically Annotated Learning Objects
  2. 2025Generate-Then-Validate: A Novel Question Generation Approach Using Small Language Models
  3. 2025Transforming Questions and Documents for Semantically Aligned Retrieval-Augmented Generation
  4. 2024Prompting-based Synthetic Data Generation for Few-Shot Question Answering
  5. 2026EAR: Entity-Aware Partitioning Approach for Retrieval-Augmented Generation Development
  6. 2026KNIGHT: Knowledge Graph-Driven Multiple-Choice Question Generation with Adaptive Hardness Calibration
  7. 2023The Knowledge Alignment Problem: Bridging Human and External Knowledge for Large Language Models
  8. 2025Semantic Bridge: Universal Multi-Hop Question Generation via AMR-Driven Graph Synthesis