相关论文: Listwise Generative Retrieval Models via a Sequent…

Open-domain question answering (QA) tasks usually require the retrieval of relevant information from a large corpus to generate accurate answers. We propose a novel approach called Generator-Retriever-Generator (GRG) that combines document…

There are many approaches for training decision trees. This work introduces a novel gradient-based method for constructing decision trees that optimize arbitrary differentiable loss functions, overcoming the limitations of heuristic…

Existing large language model (LLM)-based embeddings typically adopt an encoder-only paradigm, treating LLMs as static feature extractors and overlooking their core generative strengths. We introduce GIRCSE (Generative Iterative Refinement…

Recommender systems and search engines serve as foundational elements of online platforms, with the former delivering information proactively and the latter enabling users to seek information actively. Unifying both tasks in a shared model…

Knowledge retrieval with multi-modal queries plays a crucial role in supporting knowledge-intensive multi-modal applications. However, existing methods face challenges in terms of their effectiveness and training efficiency, especially when…

Retrieval-augmented generation (RAG) with large language models (LLMs) is especially valuable in specialized domains, where precision is critical. To more specialize the LLMs into a target domain, domain-specific RAG has recently been…

A common recent approach to semantic parsing augments sequence-to-sequence models by retrieving and appending a set of training samples, called exemplars. The effectiveness of this recipe is limited by the ability to retrieve informative…

Generative retrieval-based recommendation has emerged as a promising paradigm aiming at directly generating the identifiers of the target candidates. However, in large-scale recommendation systems, this approach becomes increasingly…

Large language models (LLMs) commonly struggle with specialized or emerging topics which are rarely seen in the training corpus. Graph-based retrieval-augmented generation (GraphRAG) addresses this by structuring domain knowledge as a graph…

Sequential recommendation aims to predict a user's next action in large-scale recommender systems. While traditional methods often suffer from insufficient information interaction, recent generative recommendation models partially address…

Trustworthiness of generative language models (GLMs) is crucial in their deployment to critical decision making systems. Hence, certified risk control methods such as selective prediction and conformal prediction have been applied to…

Generative recommendation (GR) with semantic IDs (SIDs) has emerged as a promising alternative to traditional recommendation approaches due to its performance gains, capitalization on semantic information provided through language model…

Generative information retrieval (IR) has experienced substantial growth across multiple research communities (e.g., information retrieval, computer vision, natural language processing, and machine learning), and has been highly visible in…

Large Language Models (LLMs) are adept at generating responses based on information within their context. While this ability is useful for interacting with structured data like code files, another popular method, Retrieval-Augmented…

Retrieval-Augmented Generation (RAG) integrates non-parametric knowledge into Large Language Models (LLMs), typically from unstructured texts and structured graphs. While recent progress has advanced text-based RAG to multi-turn reasoning…

Generative Recommendation (GR) has demonstrated remarkable performance in next-token prediction paradigms, which relies on Semantic IDs (SIDs) to compress trillion-scale data into learnable vocabulary sequences. However, existing methods…

Generative design refers to computational design methods that can automatically conduct design exploration under constraints defined by designers. Among many approaches, topology optimization-based generative designs aim to explore diverse…

Benchmarking the performance of information retrieval (IR) is mostly conducted with a fixed set of documents (static corpora). However, in realistic scenarios, this is rarely the case and the documents to be retrieved are constantly updated…

Social goods, such as healthcare, smart city, and information networks, often produce ordered event data in continuous time. The generative processes of these event data can be very complex, requiring flexible models to capture their…

Bayesian Likelihood-Free Inference methods yield posterior approximations for simulator models with intractable likelihood. Recently, many works trained neural networks to approximate either the intractable likelihood or the posterior…