LLM4Rerank: LLM-based Auto-Reranking Framework for Recommendations

• URL: http://arxiv.org/abs/2406.12433v4
• Date: Mon, 03 Feb 2025 02:14:26 GMT
• Title: LLM4Rerank: LLM-based Auto-Reranking Framework for Recommendations
• Authors: Jingtong Gao, Bo Chen, Weiwen Liu, Xiangyang Li, Yichao Wang, Wanyu Wang, Huifeng Guo, Ruiming Tang, Xiangyu Zhao,
• Abstract summary: Reranking is a critical component in recommender systems, playing an essential role in refining the output of recommendation algorithms. We introduce a comprehensive reranking framework, designed to seamlessly integrate various reranking criteria. A customizable input mechanism is also integrated, enabling the tuning of the language model's focus to meet specific reranking needs.
• Score: 51.76373105981212
• License:
• Abstract: Reranking is a critical component in recommender systems, playing an essential role in refining the output of recommendation algorithms. Traditional reranking models have focused predominantly on accuracy, but modern applications demand consideration of additional criteria such as diversity and fairness. Existing reranking approaches often fail to harmonize these diverse criteria effectively at the model level. Moreover, these models frequently encounter challenges with scalability and personalization due to their complexity and the varying significance of different reranking criteria in diverse scenarios. In response, we introduce a comprehensive reranking framework enhanced by LLM, designed to seamlessly integrate various reranking criteria while maintaining scalability and facilitating personalized recommendations. This framework employs a fully connected graph structure, allowing the LLM to simultaneously consider multiple aspects such as accuracy, diversity, and fairness through a coherent Chain-of-Thought (CoT) process. A customizable input mechanism is also integrated, enabling the tuning of the language model's focus to meet specific reranking needs. We validate our approach using three popular public datasets, where our framework demonstrates superior performance over existing state-of-the-art reranking models in balancing multiple criteria.

Related papers

• Theoretical Analysis of KL-regularized RLHF with Multiple Reference Models [17.8627908893654]
  We introduce a comprehensive theoretical framework that includes rigorous statistical analysis and provides sample complexity guarantees. We extend our analysis to forward KL-regularized RLHF, offering new insights into sample complexity requirements.
  arXiv  Detail & Related papers  (2025-02-03T09:50:30Z)
• Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes [50.544186914115045]
  Large language models (LLMs) are increasingly embedded in everyday applications. Ensuring their alignment with the diverse preferences of individual users has become a critical challenge. We present a novel framework for few-shot steerable alignment.
  arXiv  Detail & Related papers  (2024-12-18T16:14:59Z)
• Ranked from Within: Ranking Large Multimodal Models for Visual Question Answering Without Labels [64.94853276821992]
  Large multimodal models (LMMs) are increasingly deployed across diverse applications. Traditional evaluation methods are largely dataset-centric, relying on fixed, labeled datasets and supervised metrics. We explore unsupervised model ranking for LMMs by leveraging their uncertainty signals, such as softmax probabilities.
  arXiv  Detail & Related papers  (2024-12-09T13:05:43Z)
• From Models to Systems: A Comprehensive Fairness Framework for Compositional Recommender Systems [6.295527354699332]
  Real-world recommendation systems are built on multiple models and even multiple stages. We propose a holistic framework for modeling system-level fairness. We empirically demonstrate the effectiveness of our proposed framework on synthetic and real datasets.
  arXiv  Detail & Related papers  (2024-12-05T22:59:26Z)
• Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs [76.40876036912537]
  Large Language Models (LLMs) demonstrate strong few-shot adaptability without requiring fine-tuning. Current Visual Foundation Models (VFMs) require explicit fine-tuning with sufficient tuning data. We propose a framework, LoRA Recycle, that distills a meta-LoRA from diverse pre-tuned LoRAs with a meta-learning objective.
  arXiv  Detail & Related papers  (2024-12-03T07:25:30Z)
• Optimizing Sequential Recommendation Models with Scaling Laws and Approximate Entropy [104.48511402784763]
  Performance Law for SR models aims to theoretically investigate and model the relationship between model performance and data quality. We propose Approximate Entropy (ApEn) to assess data quality, presenting a more nuanced approach compared to traditional data quantity metrics.
  arXiv  Detail & Related papers  (2024-11-30T10:56:30Z)
• Lexicographic optimization-based approaches to learning a representative model for multi-criteria sorting with non-monotonic criteria [5.374419989598479]
  This paper proposes some approaches to learning a representative model for MCS problems with non-monotonic criteria. We first define some transformation functions to map the marginal values and category thresholds into a UTA-like functional space. We then construct constraint sets to model non-monotonic criteria in MCS problems and develop optimization models to check and rectify the inconsistency of the decision maker's assignment example preference information.
  arXiv  Detail & Related papers  (2024-09-03T05:29:05Z)
• Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment [46.44464839353993]
  We introduce Rewards-in-Context (RiC), which conditions the response of a foundation model on multiple rewards in its prompt context. RiC only requires supervised fine-tuning of a single foundation model and supports dynamic adjustment for user preferences during inference time.
  arXiv  Detail & Related papers  (2024-02-15T18:58:31Z)
• Generalized Information Criteria for Structured Sparse Models [0.0]
  We propose a new Generalized Information Criteria (GIC) that takes into consideration the sparsity pattern one wishes to recover. We show that the GIC can also be used for selecting the regularization parameter within a regularized $m$-estimation framework.
  arXiv  Detail & Related papers  (2023-09-04T18:50:13Z)
• Choosing the Best of Both Worlds: Diverse and Novel Recommendations through Multi-Objective Reinforcement Learning [68.45370492516531]
  We introduce Scalarized Multi-Objective Reinforcement Learning (SMORL) for the Recommender Systems (RS) setting. SMORL agent augments standard recommendation models with additional RL layers that enforce it to simultaneously satisfy three principal objectives: accuracy, diversity, and novelty of recommendations. Our experimental results on two real-world datasets reveal a substantial increase in aggregate diversity, a moderate increase in accuracy, reduced repetitiveness of recommendations, and demonstrate the importance of reinforcing diversity and novelty as complementary objectives.
  arXiv  Detail & Related papers  (2021-10-28T13:22:45Z)

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.