# PageLLM: A Multi-Grained Reward Framework for Whole-Page Optimization with Large Language Models

arXiv: https://arxiv.org/abs/2506.09084 · HTML: https://mlsanity.com/paper/2506.09084/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Preference alignment for recommenders and RAG, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 24 of its 44 references that are in the map.
- First posted on arXiv 10 Jun 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Preference alignment for recommenders and RAG](https://mlsanity.com/alignment/preference-alignment-for-recommenders-and-rag/)

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization](https://mlsanity.com/paper/2008.07873/) (2020)
- [Variational Autoencoders for Collaborative Filtering](https://mlsanity.com/paper/1802.05814/) (2018)
- [Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach](https://mlsanity.com/paper/2305.07001/) (2023)
- [Representation Learning with Large Language Models for Recommendation](https://mlsanity.com/paper/2310.15950/) (2023)
- [M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems](https://mlsanity.com/paper/2205.08084/) (2022)
- [Data-efficient Fine-tuning for LLM-based Recommendation](https://mlsanity.com/paper/2401.17197/) (2024)
- [A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation](https://mlsanity.com/paper/2104.13030/) (2021)
- [Addressing Complex and Subjective Product-Related Queries with Customer Reviews](https://mlsanity.com/paper/1512.06863/) (2015)
- [LLM-Enhanced User-Item Interactions: Leveraging Edge Information for Optimized Recommendations](https://mlsanity.com/paper/2402.09617/) (2024)
- [Double Correction Framework for Denoising Recommendation](https://mlsanity.com/paper/2405.11272/) (2024)
- [Knowledge Plugins: Enhancing Large Language Models for Domain-Specific Recommendations](https://mlsanity.com/paper/2311.10779/) (2023)
- [PBNR: Prompt-based News Recommender System](https://mlsanity.com/paper/2304.07862/) (2023)
- [Multimodality Invariant Learning for Multimedia-Based New Item Recommendation](https://mlsanity.com/paper/2405.15783/) (2024)
- [Aligning Large Language Models via Fine-grained Supervision](https://mlsanity.com/paper/2406.02756/) (2024)
- [RecRec: Algorithmic Recourse for Recommender Systems](https://mlsanity.com/paper/2308.14916/) (2023)

## Built on by (most cited first, 2 of 2)

- [Teaching Time Series to See and Speak: Forecasting with Aligned Visual and Textual Perspectives](https://mlsanity.com/paper/2506.24124/) (2025)
- [AnyJev Technical Report](https://mlsanity.com/paper/2610.00831/) (2026)

## Abstract (arXiv)

Whole-page optimization (WPO) decides how search and recommendation results are surfaced to users, and large language models (LLMs) open a new route to it by treating page generation as sequence generation. Adapting LLMs to web-scale WPO, however, remains bottlenecked by the need for costly human annotations and by the mismatched granularity between page-level coherence and item-level placement. In this work we show that these two challenges are coupled: implicit user feedback alone suffices for alignment, provided the reward signal is decoupled into two complementary granularities. We propose PageLLM, a reward-based fine-tuning framework that (i) turns implicit feedback into four contrastive preference-pair families covering relevance, ranking, diversity, and redundancy, (ii) learns a coarse page-level reward and a fine item-level reward that captures engagement-sensitive position swaps, and (iii) combines both rewards in PPO-based RLHF over a pre-trained LLM. Extensive experiments on seven Amazon categories against eleven baselines show that neither reward alone is sufficient -- dropping the page-level or item-level signal reduces NDCG@100 by 17.8% and 15.2% respectively, whereas the joint reward improves NDCG@100 by up to 46.8%. Deployed in a 10M-user online A/B test, PageLLM raises GMV by 0.44% and click-through rate by 0.14%, confirming that multi-grained rewards from implicit feedback scale to production WPO. Code and data are available at an anonymized repository.