# On the Memorization Behavior of LLMs in Generative Recommendation: Observations, Implications, and Training Strategies

arXiv: https://arxiv.org/abs/2606.17276 · HTML: https://mlsanity.com/paper/2606.17276/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 46 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [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)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [Deduplicating Training Data Makes Language Models Better](https://mlsanity.com/paper/2107.06499/) (2021)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering](https://mlsanity.com/paper/1602.01585/) (2016)
- [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)
- [Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation](https://mlsanity.com/paper/2311.09049/) (2023)
- [Learnable Item Tokenization for Generative Recommendation](https://mlsanity.com/paper/2405.07314/) (2024)
- [Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy](https://mlsanity.com/paper/2210.17546/) (2022)
- [Large Language Models for Generative Recommendation: A Survey and Visionary Discussions](https://mlsanity.com/paper/2309.01157/) (2023)
- [IDGenRec: LLM-RecSys Alignment with Textual ID Learning](https://mlsanity.com/paper/2403.19021/) (2024)
- [OneRec-Think: In-Text Reasoning for Generative Recommendation](https://mlsanity.com/paper/2510.11639/) (2025)
- [PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendations](https://mlsanity.com/paper/2510.07784/) (2025)
- [Undesirable Memorization in Large Language Models: A Survey](https://mlsanity.com/paper/2410.02650/) (2024)
- [Aligning Large Language Models with Recommendation Knowledge](https://mlsanity.com/paper/2404.00245/) (2024)
- [ActionPiece: Contextually Tokenizing Action Sequences for Generative Recommendation](https://mlsanity.com/paper/2502.13581/) (2025)
- [MiniOneRec: An Open-Source Framework for Scaling Generative Recommendation](https://mlsanity.com/paper/2510.24431/) (2025)
- [Generative Large Recommendation Models: Emerging Trends in LLMs for Recommendation](https://mlsanity.com/paper/2502.13783/) (2025)
- [Efficient Inference for Large Language Model-based Generative Recommendation](https://mlsanity.com/paper/2410.05165/) (2024)
- [Generative Explore-Exploit: Training-free Optimization of Generative Recommender Systems using LLM Optimizers](https://mlsanity.com/paper/2406.05255/) (2024)
- [GRAM: Generative Recommendation via Semantic-aware Multi-granular Late Fusion](https://mlsanity.com/paper/2506.01673/) (2025)
- [Understanding Generative Recommendation with Semantic IDs from a Model-scaling View](https://mlsanity.com/paper/2509.25522/) (2025)
- [Deploying Semantic ID-based Generative Retrieval for Large-Scale Podcast Discovery at Spotify](https://mlsanity.com/paper/2603.17540/) (2026)
- [Skewed Memorization in Large Language Models: Quantification and Decomposition](https://mlsanity.com/paper/2502.01187/) (2025)

## Abstract (arXiv)

Generative recommendation (GR) has emerged as a promising direction for recommender systems. Recently, large language models (LLMs) have been increasingly adopted for GR, as their rich pretrained knowledge is expected to help them generalize beyond common user behavior patterns that traditional memorization-oriented baselines can capture. However, existing LLM-based GR works largely ignore LLMs' well-known tendency to memorize, which, if present in LLMs fine-tuned for GR, would restrict their utilization of pretrained knowledge. In this work, we investigate this concern by examining one-hop memorization, where a model recommends items that are direct successors of items in the training data. We show that LLMs do this more than non-LLM-based GR models-in fact, the vast majority of their gains over GR baselines are actually on users whose target items can be predicted through one-hop memorization. We intuit that improving performance on the remaining users requires LLMs to learn richer item-item relations beyond one-hop transitions. To achieve this, we propose IIRG, a novel training strategy that teaches LLMs to capture: (1) collaborative relations derived from item co-occurrences across multiple hops in user sequences, and (2) semantic relations among items with similar themes, both of which can serve as useful recommendation signals. We show that IIRG significantly improves over LLMs trained solely with standard next-item prediction, with especially large gains for users whose test items are not covered by train-time one-hop transitions.