Large language models (LLMs) open up new horizons for sequential recommendations, owing to their remarkable language comprehension and generation capabilities. However, there are still numerous challenges that should be addressed to successfully implement sequential recommendations empowered by LLMs. Firstly, user behavior patterns are often complex, and relying solely on one-step reasoning from LLMs may lead to incorrect or task-irrelevant responses. Secondly, the prohibitively resource requirements of LLM (e.g., ChatGPT-175B) are overwhelmingly high and impractical for real sequential recommender systems. In this paper, we propose a novel Step-by-step knowLedge dIstillation fraMework for recommendation (SLIM), paving a promising path for sequential recommenders to enjoy the exceptional reasoning capabilities of LLMs in a "slim" (i.e. resource-efficient) manner. We introduce CoT prompting based on user behavior sequences for the larger teacher model. The rationales generated by the teacher model are then utilized as labels to distill the downstream smaller student model (e.g., LLaMA2-7B). In this way, the student model acquires the step-by-step reasoning capabilities in recommendation tasks. We encode the generated rationales from the student model into a dense vector, which empowers recommendation in both ID-based and ID-agnostic scenarios. Extensive experiments demonstrate the effectiveness of SLIM over state-of-the-art baselines, and further analysis showcasing its ability to generate meaningful recommendation reasoning at affordable costs.
In the evolving landscape of recommender systems, Graph Contrastive Learning (GCL) has become a prominent method for enhancing recommendation performance by alleviating the issue of data sparsity. However, existing GCL-based recommendations often overlook the control of shared information between the contrastive views. In this paper, we initially analyze and experimentally demonstrate these methods often lead to the issue of augmented representation collapse, where the representations between views become excessively similar, diminishing their distinctiveness. To address this issue, we propose the Information-Controllable Graph Contrastive Learning (IGCL) framework, a novel approach that focuses on optimizing the shared information between views to include as much relevant information for the recommendation task as possible while maintaining an appropriate level. In particular, we design the Collaborative Signals Enhanced Augmentation module to infuse the augmented representation with rich, task-relevant collaborative signals. Furthermore, the Information-Controllable Contrastive Learning module is designed to direct control over the magnitude of shared information between the contrastive views to avoid over-similarity. Extensive experiments on three public datasets demonstrate the effectiveness of IGCL, showcasing significant improvements in performance and the capability to alleviate augmented representation collapse.
Aspect-based sentiment analysis is a popular task in Natural Language Processing (NLP). Many methods utilize attention mechanisms and graph neural networks on dependency trees to identify the most relevant opinion words for aspects. However, improvements are limited due to the presence of rare words in small datasets and the inability to guarantee that each token will have a high probability of interacting with aspects. To address these challenges, we propose a Prior Knowledge Augmentation Network (PKAN) model that incorporates rich semantic information from knowledge graphs, syntactic structures, and prior probabilistic position embeddings. Specifically, to better comprehend semantic information, we design a knowledge augmentation module that constructs an adjacency matrix based on knowledge graphs, dependency trees and dataset co-occurrences. Additionally, to capture opinion words more comprehensively, we propose a probabilistic relative position embedding strategy. This strategy assumes that the semantic distribution of tokens at varying distances from the central word obeys a gaussian distribution and constrains the distance between words and aspects within one standard deviation. Experimental results on five public datasets validate the effectiveness of our model.