mlsanityData to 14 Oct 2026

Logic-Scaffolding: Personalized Aspect-Instructed Recommendation Explanation Generation using LLMs

arXiv 2312.14345 ↗First posted 22 Dec 2023cs.AI cs.CL cs.HCcited by 3

Not on the map. Why?

Abstract (arXiv)

The unique capabilities of Large Language Models (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.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 2 of its 8 references that are in the map. First posted on arXiv 22 Dec 2023.

Builds on

2 of 8 references.

References · 2

  1. 2018Explainable Recommendation: A Survey and New Perspectivescited by 210
  2. 2021Understanding the Capabilities, Limitations, and Societal Impact of Large Language Modelscited by 160

Built on by

Cited by year

Citing papers per year: 2024: 3.

3 papers.

  1. 2024A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)cited by 58
  2. 2024Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyondcited by 26
  3. 2024Large Language Model Driven Recommendationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Sequence-aware Large Language Models for Explainable Recommendation ↗
  2. 2024LANE: Logic Alignment of Non-tuning Large Language Models and Online Recommendation Systems for Explainable Reason Generation
  3. 2024ReasoningRec: Bridging Personalized Recommendations and Human-Interpretable Explanations through LLM Reasoning
  4. 2023Empowering Few-Shot Recommender Systems with Large Language Models -- Enhanced Representations
  5. 2025The Oracle and The Prism: A Decoupled and Efficient Framework for Generative Recommendation Explanation
  6. 2024Leveraging LLM Reasoning Enhances Personalized Recommender Systems
  7. 2025Generative Reasoning Recommendation via LLMs
  8. 2022Explanations from Large Language Models Make Small Reasoners Better