# Contrastive Learning for Knowledge-Based Question Generation in Large Language Models

arXiv: https://arxiv.org/abs/2409.13994 · HTML: https://mlsanity.com/paper/2409.13994/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 21 Sep 2024.

## Builds on (most cited first, 14 of 14)

- [Large Language Models: A Survey](https://mlsanity.com/paper/2402.06196/) (2024)
- [On the Planning Abilities of Large Language Models : A Critical Investigation](https://mlsanity.com/paper/2305.15771/) (2023)
- [NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space](https://mlsanity.com/paper/2309.14616/) (2023)
- [Survival Prediction Across Diverse Cancer Types Using Neural Networks](https://mlsanity.com/paper/2404.08713/) (2024)
- [How Useful are Educational Questions Generated by Large Language Models?](https://mlsanity.com/paper/2304.06638/) (2023)
- [Research on Adverse Drug Reaction Prediction Model Combining Knowledge Graph Embedding and Deep Learning](https://mlsanity.com/paper/2407.16715/) (2024)
- [Adaptive Friction in Deep Learning: Enhancing Optimizers with Sigmoid and Tanh Function](https://mlsanity.com/paper/2408.11839/) (2024)
- [A comparative study of generative adversarial networks for image recognition algorithms based on deep learning and traditional methods](https://mlsanity.com/paper/2408.03568/) (2024)
- [Dynamic Hypergraph-Enhanced Prediction of Sequential Medical Visits](https://mlsanity.com/paper/2408.07084/) (2024)
- [Algorithm Research of ELMo Word Embedding and Deep Learning Multimodal Transformer in Image Description](https://mlsanity.com/paper/2408.06357/) (2024)
- [Applying Conditional Generative Adversarial Networks for Imaging Diagnosis](https://mlsanity.com/paper/2408.02074/) (2024)
- [Text classification optimization algorithm based on graph neural network](https://mlsanity.com/paper/2408.15257/) (2024)
- [Enhancing Convolutional Neural Networks with Higher-Order Numerical Difference Methods](https://mlsanity.com/paper/2409.04977/) (2024)
- [Enhancing Deep Learning with Optimized Gradient Descent: Bridging Numerical Methods and Neural Network Training](https://mlsanity.com/paper/2409.04707/) (2024)

## Built on by (most cited first, 8 of 8)

- [Self-Supervised Graph Neural Networks for Enhanced Feature Extraction in Heterogeneous Information Networks](https://mlsanity.com/paper/2410.17617/) (2024)
- [Optimizing YOLOv5s Object Detection through Knowledge Distillation algorithm](https://mlsanity.com/paper/2410.12259/) (2024)
- [Adversarial Neural Networks in Medical Imaging Advancements and Challenges in Semantic Segmentation](https://mlsanity.com/paper/2410.13099/) (2024)
- [Graph Neural Network-Based Entity Extraction and Relationship Reasoning in Complex Knowledge Graphs](https://mlsanity.com/paper/2411.15195/) (2024)
- [Balancing Innovation and Privacy: Data Security Strategies in Natural Language Processing Applications](https://mlsanity.com/paper/2410.08553/) (2024)
- [A Recommendation Model Utilizing Separation Embedding and Self-Attention for Feature Mining](https://mlsanity.com/paper/2410.15026/) (2024)
- [Deep Learning for Medical Text Processing: BERT Model Fine-Tuning and Comparative Study](https://mlsanity.com/paper/2410.20792/) (2024)
- [Predicting Liquidity Coverage Ratio with Gated Recurrent Units: A Deep Learning Model for Risk Management](https://mlsanity.com/paper/2410.19211/) (2024)

## Abstract (arXiv)

With the rapid development of artificial intelligence technology, especially the increasingly widespread application of question-and-answer systems, high-quality question generation has become a key component in supporting the development of these systems. This article focuses on knowledge-based question generation technology, which aims to enable computers to simulate the human questioning process based on understanding specific texts or knowledge bases. In light of the issues of hallucination and knowledge gaps present in large-scale language models when applied to knowledge-intensive tasks, this paper proposes an enhanced question generation method that incorporates contrastive learning. This method utilizes multiple models to jointly mine domain knowledge and uses contrastive learning to guide the model in reducing noise and hallucinations in generation. Experimental results show that by designing prompts containing contrasting examples, the model's performance in question generation improves considerably, particularly when contrasting instructions and examples are used simultaneously, leading to the highest quality of generated questions and improved accuracy. These results demonstrate that the method proposed in this study, which combines contrasting context and chain-of-thought prompts, can effectively improve both the quality and the practicality of question generation.