mlsanityData to 7 Oct 2026

NeSy is alive and well: A LLM-driven symbolic approach for better code comment data generation and classification

arXiv 2402.16910 ↗First posted 25 Feb 2024cs.SE cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

We present a neuro-symbolic (NeSy) workflow combining a symbolic-based learning technique with a large language model (LLM) agent to generate synthetic data for code comment classification in the C programming language. We also show how generating controlled synthetic data using this workflow fixes some of the notable weaknesses of LLM-based generation and increases the performance of classical machine learning models on the code comment classification task. Our best model, a Neural Network, achieves a Macro-F1 score of 91.412% with an increase of 1.033% after data augmentation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 28 references that are in the map. First posted on arXiv 25 Feb 2024.

Builds on

23 of 28 references.

References · 23

  1. 2023A Survey of Large Language Modelscited by 2,537
  2. 2023Scaling Data-Constrained Language Modelscited by 391
  3. 2020Neurosymbolic AI: The 3rd Wavecited by 253
  4. 2023ADaPT: As-Needed Decomposition and Planning with Language Modelscited by 172
  5. 2023Machine Learning for Synthetic Data Generation: A Reviewcited by 118
  6. 2023Decomposing Uncertainty for Large Language Models through Input Clarification Ensemblingcited by 113
  7. 2023Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limitationscited by 96
  8. 2022Compositional Semantic Parsing with Large Language Modelscited by 95
  9. 2023A Survey of Large Language Models for Code: Evolution, Benchmarking, and Future Trendscited by 66
  10. 2024Comprehensive Exploration of Synthetic Data Generation: A Surveycited by 59
  11. 2022SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Modelscited by 38
  12. 2022Is a Question Decomposition Unit All We Need?cited by 37
11 more
  1. 2023Natural Language Decomposition and Interpretation of Complex Utterancescited by 10
  2. 2023Does Synthetic Data Make Large Language Models More Efficient?cited by 8
  3. 2024"Understanding AI": Semantic Grounding in Large Language Modelscited by 7
  4. 2022ZEROTOP: Zero-Shot Task-Oriented Semantic Parsing using Large Language Modelscited by 6
  5. 2023NeSIG: A Neuro-Symbolic Method for Learning to Generate Planning Problemscited by 6
  6. 2014Semantic Composition and Decomposition: From Recognition to Generationcited by 3
  7. 2024Distilling LLMs' Decomposition Abilities into Compact Language Modelscited by 3
  8. 2023Mitigating Data Scarcity for Large Language Modelscited by 2
  9. 2023A ML-LLM pairing for better code comment classificationcited by 2
  10. 2022Semantic Decomposition Improves Learning of Large Language Models on EHR Datacited by 1
  11. 2023Generative AI for Software Metadata: Overview of the Information Retrieval in Software Engineering Track at FIRE 2023cited by 1

Built on by

Not cited yet.