Related papers: CAT-ID$^2$: Category-Tree Integrated Document Iden…

Generative retrieval (GR) maps queries directly to document identifiers (docids) using parametric knowledge, However, this design makes corpus expansion costly: adding new documents requires updating model parameters to encode new…

This paper focuses on the dynamic optimization of the Retrieval-Augmented Generation (RAG) architecture. It proposes a state-aware dynamic knowledge retrieval mechanism to enhance semantic understanding and knowledge scheduling efficiency…

Generative recommendation frameworks typically represent items as discrete Semantic IDs (SIDs). While existing studies have sought to enhance SID construction by incorporating multimodal content, collaborative signals, or more advanced…

The results of information retrieval (IR) are usually presented in the form of a ranked list of candidate documents, such as web search for humans and retrieval-augmented generation for large language models (LLMs). List-aware retrieval…

Semantic identifiers (IDs) have proven effective in adapting large language models for generative recommendation and retrieval. However, existing methods often suffer from semantic ID conflicts, where semantically similar documents (or…

Traditional query expansion techniques for addressing vocabulary mismatch problems in information retrieval are context-sensitive and may lead to performance degradation. As an alternative, document expansion research has gained attention,…

Retrieval-Augmented Generation (RAG) has gained significant attention in recent years for its potential to enhance natural language understanding and generation by combining large-scale retrieval systems with generative models. RAG…

Naive Retrieval-Augmented Generation (RAG) focuses on individual documents during retrieval and, as a result, falls short in handling networked documents which are very popular in many applications such as citation graphs, social media, and…

Retrieval-Augmented Generation (RAG) has emerged as a promising approach to address key limitations of Large Language Models (LLMs), such as hallucination, outdated knowledge, and lacking reference. However, current RAG frameworks often…

A generative design based on topology optimization provides diverse alternatives as entities in a computational model with a high design degree. However, as the diversity of the generated alternatives increases, the cognitive burden on…

Generative retrieval is a promising new neural retrieval paradigm that aims to optimize the retrieval pipeline by performing both indexing and retrieval with a single transformer model. However, this new paradigm faces challenges with…

Recently, a new paradigm called Differentiable Search Index (DSI) has been proposed for document retrieval, wherein a sequence-to-sequence model is learned to directly map queries to relevant document identifiers. The key idea behind DSI is…

Retrieval-augmented generation (RAG) integrates large language models ( LLM s) with retrievers to access external knowledge, improving the factuality of LLM generation in knowledge-grounded tasks. To optimize the RAG performance, most…

Large language models (LLMs) inherently display hallucinations since the precision of generated texts cannot be guaranteed purely by the parametric knowledge they include. Although retrieval-augmented generation (RAG) systems enhance the…

This paper investigates synthetic data generation strategies in developing generative retrieval models for domain-specific corpora, thereby addressing the scalability challenges inherent in manually annotating in-domain queries. We study…

Large language models (LLMs) inevitably exhibit hallucinations since the accuracy of generated texts cannot be secured solely by the parametric knowledge they encapsulate. Although retrieval-augmented generation (RAG) is a practicable…

Lifelong user modeling, which leverages users' long-term behavior sequences for CTR prediction, has been widely applied in personalized services. Existing methods generally adopted a two-stage "retrieval-refinement" strategy to balance…

Mapping a search query to a set of relevant categories in the product taxonomy is a significant challenge in e-commerce search for two reasons: 1) Training data exhibits severe class imbalance problem due to biased click behavior, and 2)…

Large Language Models (LLMs) are pre-trained on large-scale corpora and excel in numerous general natural language processing (NLP) tasks, such as question answering (QA). Despite their advanced language capabilities, when it comes to…

Gait recognition offers a non-intrusive biometric solution by identifying individuals through their walking patterns. Although discriminative models have achieved notable success in this domain, the full potential of generative models…