Automating Personalization: Prompt Optimization for Recommendation Reranking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Chen, Yang, Mingdai, Liu, Zhiwei, Li, Pan, Pang, Linsey, Wen, Qingsong, Yu, Philip
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916675146743808
author Wang, Chen
Yang, Mingdai
Liu, Zhiwei
Li, Pan
Pang, Linsey
Wen, Qingsong
Yu, Philip
author_facet Wang, Chen
Yang, Mingdai
Liu, Zhiwei
Li, Pan
Pang, Linsey
Wen, Qingsong
Yu, Philip
contents Modern recommender systems increasingly leverage large language models (LLMs) for reranking to improve personalization. However, existing approaches face two key limitations: (1) heavy reliance on manually crafted prompts that are difficult to scale, and (2) inadequate handling of unstructured item metadata that complicates preference inference. We present AGP (Auto-Guided Prompt Refinement), a novel framework that automatically optimizes user profile generation prompts for personalized reranking. AGP introduces two key innovations: (1) position-aware feedback mechanisms for precise ranking correction, and (2) batched training with aggregated feedback to enhance generalization.
format Preprint
id arxiv_https___arxiv_org_abs_2504_03965
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Automating Personalization: Prompt Optimization for Recommendation Reranking
Wang, Chen
Yang, Mingdai
Liu, Zhiwei
Li, Pan
Pang, Linsey
Wen, Qingsong
Yu, Philip
Information Retrieval
Modern recommender systems increasingly leverage large language models (LLMs) for reranking to improve personalization. However, existing approaches face two key limitations: (1) heavy reliance on manually crafted prompts that are difficult to scale, and (2) inadequate handling of unstructured item metadata that complicates preference inference. We present AGP (Auto-Guided Prompt Refinement), a novel framework that automatically optimizes user profile generation prompts for personalized reranking. AGP introduces two key innovations: (1) position-aware feedback mechanisms for precise ranking correction, and (2) batched training with aggregated feedback to enhance generalization.
title Automating Personalization: Prompt Optimization for Recommendation Reranking
topic Information Retrieval
url https://arxiv.org/abs/2504.03965