DRDT：面向基于大语言模型的序列推荐的融合发散思维的动态反思方法
DRDT: Dynamic Reflection with Divergent Thinking for LLM-based Sequential Recommendation
AI总结：
针对大语言模型现有推理策略在序列推荐中效果不佳的问题，提出融合发散思维的动态反思推理原则，通过协作检索、多维度偏好抽象和动态反思，无需微调即可让7B模型在三个数据集上超越GPT-Turbo-3.5。
摘要：
大语言模型（LLM）的兴起引发了学界对其在序列推荐任务应用的兴趣，因为它们能提供辅助的物品信息。然而，由于序列推荐固有的复杂性，例如跨数据集的序列模式、序列内的噪声以及用户偏好的时间演化，现有的LLM推理策略（如上下文学习和思维链）并不能完全发挥效用。为应对这些挑战，我们在检索-重排序框架内提出了一种新颖的推理原则：融合发散思维的动态反思（Dynamic Reflection with Divergent Thinking，即DRDT）。我们的方法首先采用协作式上下文示例检索器，该检索器收集展现出协作行为的序列作为上下文示例。随后，我们从多个维度抽象出高层用户偏好，从而更细致地理解用户兴趣，并规避原始序列中的噪声。我们方法的核心是动态反思，这一过程通过探查、批判和反思来模拟人类学习，利用用户反馈在时间维度上更有效地针对目标用户调整分析。我们使用六个预训练LLM在三个数据集上评估了我们的方法。在这些模型上观察到的优异性能证明了我们推理策略的有效性，值得注意的是，这一效果无需对LLM进行微调即可实现。借助我们的原则，我们使用7b模型（例如Vicuna-7b和Openchat-7b）在三个数据集的NDCG@10指标上超越了GPT-Turbo-3.5。本研究不仅凸显了LLM在增强序列推荐系统方面的潜力，还强调了开发定制化推理策略以充分发挥其能力的重要性。
英文摘要：
The rise of Large Language Models (LLMs) has sparked interest in their application to sequential recommendation tasks as they can provide supportive item information. However, due to the inherent complexities of sequential recommendation, such as sequential patterns across datasets, noise within sequences, and the temporal evolution of user preferences, existing LLM reasoning strategies, such as in-context learning and chain-of-thought are not fully effective. To address these challenges, we introduce a novel reasoning principle: Dynamic Reflection with Divergent Thinking within a retriever-reranker framework. Our approach starts with a collaborative in-context demonstration retriever, which collects sequences exhibiting collaborative behaviors as in-context examples. Following this, we abstract high-level user preferences across multiple aspects, providing a more nuanced understanding of user interests and circumventing the noise within the raw sequences. The cornerstone of our methodology is dynamic reflection, a process that emulates human learning through probing, critiquing, and reflecting, using user feedback to tailor the analysis more effectively to the target user in a temporal manner. We evaluate our approach on three datasets using six pre-trained LLMs. The superior performance observed across these models demonstrates the efficacy of our reasoning strategy, notably achieved without the need to fine-tune the LLMs. With our principle, we managed to outperform GPT-Turbo-3.5 on three datasets using 7b models e.g., Vicuna-7b and Openchat-7b on NDCG@10. This research not only highlights the potential of LLMs in enhancing sequential recommendation systems but also underscores the importance of developing tailored reasoning strategies to fully harness their capabilities.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
