Related papers: Optimizing Recall or Relevance? A Multi-Task Multi…
Accurate multi-modal document retrieval is crucial for Retrieval-Augmented Generation (RAG), yet existing benchmarks do not fully capture real-world challenges with their current design. We introduce REAL-MM-RAG, an automatically generated…
Relevance judgments are crucial for evaluating information retrieval systems, but traditional human-annotated labels are time-consuming and expensive. As a result, many researchers turn to automatic alternatives to accelerate method…
With the growing popularity of LLM agents and RAG, it has become increasingly important to retrieve documents that are essential for solving a task, even when their connection to the task is indirect or implicit. Addressing this problem…
Modern search systems rely on a fast first stage retriever to fetch relevant items from a massive catalog of items. Deployed search systems often use user engagement signals to supervise bi-encoder retriever training at scale, because these…
Neural-based multi-task learning (MTL) has been successfully applied to many recommendation applications. However, these MTL models (e.g., MMoE, PLE) did not consider feature interaction during the optimization, which is crucial for…
The increasing availability and diversity of multimodal data in recommender systems offer new avenues for enhancing recommendation accuracy and user satisfaction. However, these systems must contend with high-dimensional, sparse user-item…
User and item reviews are valuable for the construction of recommender systems. In general, existing review-based methods for recommendation can be broadly categorized into two groups: the siamese models that build static user and item…
Recent Long-Context Language Models (LCLMs) can process hundreds of thousands of tokens in a single prompt, enabling new opportunities for knowledge-intensive multi-hop reasoning by integrating large sets of retrieved documents or, in some…
Iterative summarization based reasoning frameworks such as InftyThink enable long-horizon reasoning in large language models (LLMs) by controlling context growth, but they repeatedly regenerate similar reasoning strategies across tasks. We…
Vocabulary mismatch is a central problem in information retrieval (IR), i.e., the relevant documents may not contain the same (symbolic) terms of the query. Recently, neural representations have shown great success in capturing semantic…
Hallucination is a major concern in LLM-driven service systems, necessitating explicit knowledge grounding for compliance-guaranteed responses. In this paper, we introduce Retrieval-Augmented Learning-to-Match (RAL2M), a novel framework…
Modern retrieval systems are often driven by an underlying machine learning model. The goal of such systems is to identify and possibly rank the few most relevant items for a given query or context. Thus, such systems are typically…
Deep search has recently emerged as a promising paradigm for enabling agents to retrieve fine-grained historical information without heavy memory pre-managed. However, existing deep search agents for memory system repeat past error…
The objective of text-to-image (T2I) personalization is to customize a diffusion model to a user-provided reference concept, generating diverse images of the concept aligned with the target prompts. Conventional methods representing the…
Accurate query-product relevance labeling is indispensable to generate ground truth dataset for search ranking in e-commerce. Traditional approaches for annotating query-product pairs rely on human-based labeling services, which is…
Multi-Instance Multi-Label learning (MIML) models complex objects (bags), each of which is associated with a set of interrelated labels and composed with a set of instances. Current MIML solutions still focus on a single-type of objects and…
We introduce ``Idea to Image,'' a system that enables multimodal iterative self-refinement with GPT-4V(ision) for automatic image design and generation. Humans can quickly identify the characteristics of different text-to-image (T2I) models…
Multi-Task Reinforcement Learning aims at developing agents that are able to continually evolve and adapt to new scenarios. However, this goal is challenging to achieve due to the phenomenon of catastrophic forgetting and the high demand of…
Training Learning-to-Rank models for e-commerce product search ranking can be challenging due to the lack of a gold standard of ranking relevance. In this paper, we decompose ranking relevance into content-based and engagement-based…
We introduce a novel large language model (LLM)-driven agent framework, which iteratively refines queries and filters contextual evidence by leveraging dynamically evolving knowledge. A defining feature of the system is its decoupling of…