Improving Diversity of Commonsense Generation by Large Language Models via In-Context Learning
This addresses a gap in generative commonsense reasoning for AI applications, though it is incremental as it builds on existing in-context learning techniques.
The paper tackles the lack of diversity in commonsense generation by large language models, proposing a method that improves diversity while maintaining quality, achieving an ideal balance on three benchmark datasets.
Generative Commonsense Reasoning (GCR) requires a model to reason about a situation using commonsense knowledge, while generating coherent sentences. Although the quality of the generated sentences is crucial, the diversity of the generation is equally important because it reflects the model's ability to use a range of commonsense knowledge facts. Large Language Models (LLMs) have shown proficiency in enhancing the generation quality across various tasks through in-context learning (ICL) using given examples without the need for any fine-tuning. However, the diversity aspect in LLM outputs has not been systematically studied before. To address this, we propose a simple method that diversifies the LLM generations, while preserving their quality. Experimental results on three benchmark GCR datasets show that our method achieves an ideal balance between the quality and diversity. Moreover, the sentences generated by our proposed method can be used as training data to improve diversity in existing commonsense generators.