Related papers: Mine and Refine: Optimizing Graded Relevance in E-…

Cloud computing is emerging as a revolutionary computing paradigm which pro-vides a flexible and economic strategy for data management and resource sharing. Security and privacy become major concerns in the cloud scenario, for which…

Retrieval-Augmented Language Models (RALMs) face significant challenges in reducing factual errors, particularly in document relevance evaluation and knowledge integration. We introduce a framework for structured relevance assessment that…

Dense retrieval models are typically fine-tuned with contrastive learning objectives that require binary relevance judgments, even though relevance is inherently graded. We analyze how graded relevance scores and the threshold used to…

Image-text retrieval requires the system to bridge the heterogenous gap between vision and language for accurate retrieval while keeping the network lightweight-enough for efficient retrieval. Existing trade-off solutions mainly study from…

This paper mainly describes our winning solution (team name: www) to Amazon ESCI Challenge of KDD CUP 2022, which achieves a NDCG score of 0.9043 and wins the first place on task 1: the query-product ranking track. In this competition,…

Retrieval models based on dense representations in semantic space have become an indispensable branch for first-stage retrieval. These retrievers benefit from surging advances in representation learning towards compressive global…

Large Language Models (LLMs) face significant challenges in specialized domains like law, where precision and domain-specific knowledge are critical. This paper presents a streamlined two-stage framework consisting of Retrieval and…

Building a search relevance model that achieves both low latency and high performance is a long-standing challenge in the search industry. To satisfy the millisecond-level response requirements of online systems while retaining the…

Retrieval augmentation, which enhances downstream models by a knowledge retriever and an external corpus instead of by merely increasing the number of model parameters, has been successfully applied to many natural language processing (NLP)…

With the rapid advancement of multi-modal large language models (MLLMs) in recent years, the foundational Contrastive Language-Image Pretraining (CLIP) framework has been successfully extended to MLLMs, enabling more powerful and universal…

Retrieval-augmented generation (RAG) frameworks enable large language models (LLMs) to retrieve relevant information from a knowledge base and incorporate it into the context for generating responses. This mitigates hallucinations and…

Recent large language models (LLM) are leveraging human feedback to improve their generation quality. However, human feedback is costly to obtain, especially during inference. In this work, we propose LLMRefine, an inference time…

Large language models (LLMs) have increasingly been explored as powerful text embedders. Existing LLM-based text embedding approaches often leverage the embedding of the final token, typically a reserved special token such as [EOS].…

We present a production-oriented semantic retrieval system for Uber Eats that unifies retrieval across stores, dishes, and grocery/retail items. Our approach fine-tunes a Qwen2 two-tower base model using hundreds of millions of…

This paper tackles the pressing challenge of preserving semantic meaning in communication systems constrained by limited bandwidth. We introduce a novel reinforcement learning framework that achieves per-dimension unequal error protection…

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…

Although synthetic data has changed various aspects of information retrieval (IR) pipelines, the main training paradigm remains: contrastive learning with binary relevance labels, where one positive document is compared against several…

Recent advances in large language models (LLMs) have yielded impressive performance on various tasks, yet they often depend on high-quality feedback that can be costly. Self-refinement methods attempt to leverage LLMs' internal evaluation…

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…

Large language models (LLMs), with advanced linguistic capabilities, have been employed in reranking tasks through a sequence-to-sequence approach. In this paradigm, multiple passages are reranked in a listwise manner and a textual reranked…