Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Rahdari, Behnam, Ding, Hao, Fan, Ziwei, Ma, Yifei, Chen, Zhuotong, Deoras, Anoop, Kveton, Branislav
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2312.14345
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911760090398720
author Rahdari, Behnam
Ding, Hao
Fan, Ziwei
Ma, Yifei
Chen, Zhuotong
Deoras, Anoop
Kveton, Branislav
author_facet Rahdari, Behnam
Ding, Hao
Fan, Ziwei
Ma, Yifei
Chen, Zhuotong
Deoras, Anoop
Kveton, Branislav
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2312_14345
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Logic-Scaffolding: Personalized Aspect-Instructed Recommendation Explanation Generation using LLMs
Rahdari, Behnam
Ding, Hao
Fan, Ziwei
Ma, Yifei
Chen, Zhuotong
Deoras, Anoop
Kveton, Branislav
Artificial Intelligence
Computation and Language
Human-Computer Interaction
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.
title Logic-Scaffolding: Personalized Aspect-Instructed Recommendation Explanation Generation using LLMs
topic Artificial Intelligence
Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/2312.14345