User Feedback Alignment for LLM-powered Exploration in Large-scale Recommendation Systems

• URL: http://arxiv.org/abs/2504.05522v2
• Date: Fri, 11 Apr 2025 22:16:00 GMT
• Title: User Feedback Alignment for LLM-powered Exploration in Large-scale Recommendation Systems
• Authors: Jianling Wang, Yifan Liu, Yinghao Sun, Xuejian Ma, Yueqi Wang, He Ma, Zhengyang Su, Minmin Chen, Mingyan Gao, Onkar Dalal, Ed H. Chi, Lichan Hong, Ningren Han, Haokai Lu,
• Abstract summary: Exploration, the act of broadening user experiences beyond their established preferences, is challenging in large-scale recommendation systems.<n>This paper introduces a novel approach combining hierarchical planning with LLM inference-time scaling to improve recommendation relevancy without compromising novelty.
• Score: 26.652050105571206
• License: http://creativecommons.org/licenses/by/4.0/
• 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 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. While using LLMs to plan for the next novel user interest, this paper introduces a novel approach combining hierarchical planning with LLM inference-time scaling 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.

Related papers

• Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models [50.16340812031201]
  We show that large language models (LLMs) do not update their beliefs as expected from the Bayesian framework.<n>We teach the LLMs to reason in a Bayesian manner by training them to mimic the predictions of an optimal Bayesian model.
  arXiv  Detail & Related papers  (2025-03-21T20:13:04Z)
• UQABench: Evaluating User Embedding for Prompting LLMs in Personalized Question Answering [39.79275025010785]
  name is a benchmark designed to evaluate the effectiveness of user embeddings in prompting large language models for personalization.<n>We conduct extensive experiments on various state-of-the-art methods for modeling user embeddings.
  arXiv  Detail & Related papers  (2025-02-26T14:34:00Z)
• From Selection to Generation: A Survey of LLM-based Active Learning [153.8110509961261]
  Large Language Models (LLMs) have been employed for generating entirely new data instances and providing more cost-effective annotations.<n>This survey aims to serve as an up-to-date resource for researchers and practitioners seeking to gain an intuitive understanding of LLM-based AL techniques.
  arXiv  Detail & Related papers  (2025-02-17T12:58:17Z)
• Real-Time Personalization for LLM-based Recommendation with Customized In-Context Learning [57.28766250993726]
  This work explores adapting to dynamic user interests without any model updates. Existing Large Language Model (LLM)-based recommenders often lose the in-context learning ability during recommendation tuning. We propose RecICL, which customizes recommendation-specific in-context learning for real-time recommendations.
  arXiv  Detail & Related papers  (2024-10-30T15:48:36Z)
• LLMEmb: Large Language Model Can Be a Good Embedding Generator for Sequential Recommendation [57.49045064294086]
  Large Language Model (LLM) has the ability to capture semantic relationships between items, independent of their popularity.<n>We introduce LLMEmb, a novel method leveraging LLM to generate item embeddings that enhance Sequential Recommender Systems (SRS) performance.
  arXiv  Detail & Related papers  (2024-09-30T03:59:06Z)
• HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modeling [21.495443162191332]
  Large Language Models (LLMs) have achieved remarkable success in various fields, prompting several studies to explore their potential in recommendation systems. We propose a novel Hierarchical Large Language Model (HLLM) architecture designed to enhance sequential recommendation systems. HLLM achieves excellent scalability, with the largest configuration utilizing 7B parameters for both item feature extraction and user interest modeling.
  arXiv  Detail & Related papers  (2024-09-19T13:03:07Z)
• Incorporate LLMs with Influential Recommender System [34.5820082133773]
  proactive recommender systems recommend a sequence of items to guide user interest in the target item. Existing methods struggle to construct a coherent influence path that builds up with items the user is likely to enjoy. We introduce a novel approach named LLM-based Influence Path Planning (LLM-IPP) Our approach maintains coherence between consecutive recommendations and enhances user acceptability of the recommended items.
  arXiv  Detail & Related papers  (2024-09-07T13:41:37Z)
• LLMs for User Interest Exploration in Large-scale Recommendation Systems [16.954465544444766]
  Traditional recommendation systems are subject to a strong feedback loop by learning from and reinforcing past user-item interactions. We introduce a hybrid hierarchical framework combining Large Language Models (LLMs) and classic recommendation models for user interest exploration. We showcase the efficacy of this approach on an industrial-scale commercial platform serving billions of users.
  arXiv  Detail & Related papers  (2024-05-25T21:57:36Z)
• Improve Temporal Awareness of LLMs for Sequential Recommendation [61.723928508200196]
  Large language models (LLMs) have demonstrated impressive zero-shot abilities in solving a wide range of general-purpose tasks. LLMs fall short in recognizing and utilizing temporal information, rendering poor performance in tasks that require an understanding of sequential data. We propose three prompting strategies to exploit temporal information within historical interactions for LLM-based sequential recommendation.
  arXiv  Detail & Related papers  (2024-05-05T00:21:26Z)
• User-LLM: Efficient LLM Contextualization with User Embeddings [23.226164112909643]
  User-LLM is a novel framework that leverages user embeddings to directly contextualize large language models with user history interactions. Our approach achieves significant efficiency gains by representing user timelines directly as embeddings, leading to substantial inference speedups of up to 78.1X.
  arXiv  Detail & Related papers  (2024-02-21T08:03:27Z)
• Large Language Models for Intent-Driven Session Recommendations [34.64421003286209]
  We introduce a novel ISR approach, utilizing the advanced reasoning capabilities of large language models (LLMs) We introduce an innovative prompt optimization mechanism that iteratively self-reflects and adjusts prompts. This new paradigm empowers LLMs to discern diverse user intents at a semantic level, leading to more accurate and interpretable session recommendations.
  arXiv  Detail & Related papers  (2023-12-07T02:25:14Z)
• Recommender Systems in the Era of Large Language Models (LLMs) [62.0129013439038]
  Large Language Models (LLMs) have revolutionized the fields of Natural Language Processing (NLP) and Artificial Intelligence (AI) We conduct a comprehensive review of LLM-empowered recommender systems from various aspects including Pre-training, Fine-tuning, and Prompting.
  arXiv  Detail & Related papers  (2023-07-05T06:03:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.