Year: 2025
Type: preprint
Abstract: Exploration, the act of broadening user experiences beyond their established preferences, is challenging in large-scale recommendation systems due to feedback loops and limited signals on user exploration patterns. Large Language Models (LLMs) offer potential solutions by leveraging their world knowledge to recommend novel content outside these loops. A key challenge is aligning LLMs with user preferences while preserving their knowledge and reasoning. To enhance planning for new user interests using LLMs, this paper introduces a novel approach that combines hierarchical planning with LLM inference-time scaling. This method aims to improve recommendation relevancy without compromising novelty. We decouple novelty and user-alignment, training separate LLMs for each objective. We then scale up the novelty-focused LLM's inference and select the best-of-n predictions using the user-aligned LLM. Live experiments demonstrate efficacy, showing significant gains in both user satisfaction (measured by watch activity and active user counts) and exploration diversity.
Source: arXiv (Cornell University)
Authors: Wang, Jianling, Liu, Yifan, Sun, Yinghao, Ma, Xuejian, Wang, Yueqi, Ma, He, Su, Zhengyang, Chen, Minmin, Gao, Mingyan, Dalal, Onkar, Chi, Ed H., Hong, Lichan, Han, Ningren, Lu, Haokai
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4416119106
Cites:
Cited by:
Related to: