ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation
- URL: http://arxiv.org/abs/2308.11131v5
- Date: Mon, 24 Jun 2024 02:44:28 GMT
- Title: ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation
- Authors: Jianghao Lin, Rong Shan, Chenxu Zhu, Kounianhua Du, Bo Chen, Shigang Quan, Ruiming Tang, Yong Yu, Weinan Zhang,
- Abstract summary: We focus on adapting and empowering a pure large language model for zero-shot and few-shot recommendation tasks.
We propose Retrieval-enhanced Large Language models (ReLLa) for recommendation tasks in both zero-shot and few-shot settings.
- Score: 43.270424225285105
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: With large language models (LLMs) achieving remarkable breakthroughs in natural language processing (NLP) domains, LLM-enhanced recommender systems have received much attention and have been actively explored currently. In this paper, we focus on adapting and empowering a pure large language model for zero-shot and few-shot recommendation tasks. First and foremost, we identify and formulate the lifelong sequential behavior incomprehension problem for LLMs in recommendation domains, i.e., LLMs fail to extract useful information from a textual context of long user behavior sequence, even if the length of context is far from reaching the context limitation of LLMs. To address such an issue and improve the recommendation performance of LLMs, we propose a novel framework, namely Retrieval-enhanced Large Language models (ReLLa) for recommendation tasks in both zero-shot and few-shot settings. For zero-shot recommendation, we perform semantic user behavior retrieval (SUBR) to improve the data quality of testing samples, which greatly reduces the difficulty for LLMs to extract the essential knowledge from user behavior sequences. As for few-shot recommendation, we further design retrieval-enhanced instruction tuning (ReiT) by adopting SUBR as a data augmentation technique for training samples. Specifically, we develop a mixed training dataset consisting of both the original data samples and their retrieval-enhanced counterparts. We conduct extensive experiments on three real-world public datasets to demonstrate the superiority of ReLLa compared with existing baseline models, as well as its capability for lifelong sequential behavior comprehension. To be highlighted, with only less than 10% training samples, few-shot ReLLa can outperform traditional CTR models that are trained on the entire training set (e.g., DCNv2, DIN, SIM). The code is available \url{https://github.com/LaVieEnRose365/ReLLa}.
Related papers
- Lost in Sequence: Do Large Language Models Understand Sequential Recommendation? [33.92662524009036]
Large Language Models (LLMs) have emerged as promising tools for recommendation thanks to their advanced textual understanding ability and context-awareness.
We propose a method that enhances the integration of sequential information into LLMs by distilling the user representations extracted from a pre-trained-SRec model into LLMs.
Our experiments show that LLM-SRec enhances LLMs' ability to understand users' item interaction sequences, ultimately leading to improved recommendation performance.
arXiv Detail & Related papers (2025-02-19T17:41:09Z) - Full-Stack Optimized Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation [44.685176786857284]
We propose ReLLaX (Retrieval-enhanced Large Language models Plus), a framework offering optimization across data, prompt, and parameter levels.
At the data level, we introduce Semantic User Behavior Retrieval (SUBR) to reduce sequence heterogeneity, making it easier for LLMs to extract key information.
For prompt-level enhancement, we employ Soft Prompt Augmentation (SPA) to inject collaborative knowledge, aligning item representations with recommendation tasks.
At the parameter level, we propose Component Fully-interactive LoRA (CFLoRA), which enhances LoRA's expressiveness by enabling interactions between its components
arXiv Detail & Related papers (2025-01-23T03:05:13Z) - 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) - SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning [70.21358720599821]
Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts.
We propose SELF-GUIDE, a multi-stage mechanism in which we synthesize task-specific input-output pairs from the student LLM.
We report an absolute improvement of approximately 15% for classification tasks and 18% for generation tasks in the benchmark's metrics.
arXiv Detail & Related papers (2024-07-16T04:41:58Z) - One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language Models [67.49462724595445]
Retrieval-augmented generation (RAG) is a promising way to improve large language models (LLMs)
We propose a novel method that involves learning scalable and pluggable virtual tokens for RAG.
arXiv Detail & Related papers (2024-05-30T03:44:54Z) - 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) - LlamaRec: Two-Stage Recommendation using Large Language Models for
Ranking [10.671747198171136]
We propose a two-stage framework using large language models for ranking-based recommendation (LlamaRec)
In particular, we use small-scale sequential recommenders to retrieve candidates based on the user interaction history.
LlamaRec consistently achieves datasets superior performance in both recommendation performance and efficiency.
arXiv Detail & Related papers (2023-10-25T06:23:48Z) - Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning [79.32236399694077]
Low-quality data in the training set are usually detrimental to instruction tuning.
We propose a novel method, termed "reflection-tuning"
This approach utilizes an oracle LLM to recycle the original training data by introspecting and enhancing the quality of instructions and responses in the data.
arXiv Detail & Related papers (2023-10-18T05:13:47Z) - Revisiting Large Language Models as Zero-shot Relation Extractors [8.953462875381888]
Relation extraction (RE) consistently involves a certain degree of labeled or unlabeled data even if under zero-shot setting.
Recent studies have shown that large language models (LLMs) transfer well to new tasks out-of-the-box simply given a natural language prompt.
This work focuses on the study of exploring LLMs as zero-shot relation extractors.
arXiv Detail & Related papers (2023-10-08T06:17:39Z) - PALR: Personalization Aware LLMs for Recommendation [7.407353565043918]
PALR aims to combine user history behaviors (such as clicks, purchases, ratings, etc.) with large language models (LLMs) to generate user preferred items.
Our solution outperforms state-of-the-art models on various sequential recommendation tasks.
arXiv Detail & Related papers (2023-05-12T17:21:33Z)
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.