paper-with-me

Papers

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

2023-12-22 · Behnam Rahdari, Hao Ding, Ziwei Fan, Yifei Ma, Zhuotong Chen, Anoop Deoras, Branislav Kveton

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.

📄 PDF Abstract BibTeX arXiv:2312.14345

Code (0)

등록된 구현이 없습니다.

Tasks

Explanation GenerationPositionText Generation

Similar Papers 제목 키워드 기반

UCEpic: Unifying Aspect Planning and Lexical Constraints for Generating Explanations in Recommendation

2022-09-28 · Jiacheng Li, Zhankui He, Jingbo Shang, Julian McAuley

Personalized natural language generation for explainable recommendations plays a key role in justifying why a recommendation might match a user's interests. Existing models usually control the generation process by aspec…

DiversityExplainable RecommendationExplanation GenerationInformativeness+1

Artful Path to Healing: Using Machine Learning for Visual Art Recommendation to Prevent and Reduce Post-Intensive Care

2024-02-23 · Bereket A. Yilma, Chan Mi Kim, Gerald C. Cupchik, Luis A. Leiva

Staying in the intensive care unit (ICU) is often traumatic, leading to post-intensive care syndrome (PICS), which encompasses physical, psychological, and cognitive impairments. Currently, there are limited intervention…

Recommendation Systems

Prompt Tuning Large Language Models on Personalized Aspect Extraction for Recommendations

2023-06-02 · Pan Li, Yuyan Wang, Ed H. Chi, Minmin Chen

Existing aspect extraction methods mostly rely on explicit or ground truth aspect information, or using data mining or machine learning approaches to extract aspects from implicit user feedback such as user reviews. It h…

Aspect ExtractionPrompt Learning

PERS: A Personalized and Explainable POI Recommender System

2017-12-20 · Baral Ramesh, Li Tao

The Location-Based Social Networks (LBSN) (e.g., Facebook) have many factors (for instance, ratings, check-in time, etc.) that play a crucial role for the Point-of-Interest (POI) recommendations. Unlike ratings, the revi…

Explainable RecommendationRecommendation Systems

Enhancing Personalized Recipe Recommendation Through Multi-Class Classification

2024-09-16 · Harish Neelam, Koushik Sai Veerella

This paper intends to address the challenge of personalized recipe recommendation in the realm of diverse culinary preferences. The problem domain involves recipe recommendations, utilizing techniques such as association…

ClassificationMulti-class Classification