Logic-Scaffolding: Personalized Aspect-Instructed Recommendation Explanation Generation using LLMs (2312.14345v2)
Abstract: The unique capabilities of LLMs, such as the natural language text generation ability, position them as strong candidates for providing explanation for recommendations. However, despite the size of the LLM, most existing models struggle to produce zero-shot explanations reliably. To address this issue, we propose a framework called Logic-Scaffolding, that combines the ideas of aspect-based explanation and chain-of-thought prompting to generate explanations through intermediate reasoning steps. In this paper, we share our experience in building the framework and present an interactive demonstration for exploring our results.
- Falcon-40B: an open large language model with state-of-the-art performance. (2023).
- Language models are few-shot learners. Advances in neural information processing systems 33 (2020), 1877–1901.
- Jacob Cohen. 2013. Statistical power analysis for the behavioral sciences. Academic press.
- F. Maxwell Harper and Joseph A. Konstan. 2015. The MovieLens Datasets: History and Context. ACM Trans. Interact. Intell. Syst. 5, 4, Article 19 (dec 2015), 19 pages.
- Understanding the capabilities, limitations, and societal impact of large language models. (2021).
- Emergent abilities of large language models. arXiv preprint arXiv:2206.07682 (2022).
- Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems 35 (2022), 24824–24837.
- Explainable recommendation: A survey and new perspectives. Foundations and Trends® in Information Retrieval 14, 1 (2020), 1–101.
Collections
Sign up for free to add this paper to one or more collections.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.