Related papers: Divide and Conquer: Towards Better Embedding-based…

Candidate retrieval is the first stage in recommendation systems, where a light-weight system is used to retrieve potentially relevant items for an input user. These candidate items are then ranked and pruned in later stages of recommender…

Retrieval with extremely long queries and documents is a well-known and challenging task in information retrieval and is commonly known as Query-by-Document (QBD) retrieval. Specifically designed Transformer models that can handle long…

In recommendation systems, users frequently engage in multiple types of behaviors, such as clicking, adding to a cart, and purchasing. However, with diversified behavior data, user behavior sequences will become very long in the short term,…

Addressing the complexity of comprehensive information retrieval, this study introduces an innovative, iterative retrieval-augmented generation system. Our approach uniquely integrates a vector-space driven re-ranking mechanism with…

Embedding-based retrieval methods construct vector indices to search for document representations that are most similar to the query representations. They are widely used in document retrieval due to low latency and decent recall…

Recent studies have shown that Dense Retrieval (DR) techniques can significantly improve the performance of first-stage retrieval in IR systems. Despite its empirical effectiveness, the application of DR is still limited. In contrast to…

Recommender Systems are tools that improve how users find relevant information in web systems, so they do not face too much information. In order to generate better recommendations, the context of information should be used in the…

In common law systems, legal professionals such as lawyers and judges rely on precedents to build their arguments. As the volume of cases has grown massively over time, effectively retrieving prior cases has become essential. Prior case…

Preference-based Reinforcement Learning (PbRL) methods provide a solution to avoid reward engineering by learning reward models based on human preferences. However, poor feedback- and sample- efficiency still remain the problems that hinder…

Retrieval-Augmented Generation (RAG) methods enhance LLM performance by efficiently filtering relevant context for LLMs, reducing hallucinations and inference cost. However, most existing RAG methods focus on single-step retrieval, which is…

Pre-trained code models have emerged as the state-of-the-art paradigm for code search tasks. The paradigm involves pre-training the model on search-irrelevant tasks such as masked language modeling, followed by the fine-tuning stage, which…

Multi-task learning (MTL) has shown effectiveness in exploiting shared information across tasks to improve generalization. MTL assumes tasks share similarities that can improve performance. In addition, boosting algorithms have demonstrated…

Generative retrieval represents a novel approach to information retrieval. It uses an encoder-decoder architecture to directly produce relevant document identifiers (docids) for queries. While this method offers benefits, current approaches…

The ever-increasing size of language models curtails their widespread availability to the community, thereby galvanizing many companies into offering access to large language models through APIs. One particular type, suitable for dense…

Reward models (RMs) are essential for aligning Large Language Models (LLMs) with human preferences. However, they often struggle with capturing complex human preferences and generalizing to unseen data. To address these challenges, we…

Text embedding models have been popular for information retrieval applications such as semantic search and Question-Answering systems based on Retrieval-Augmented Generation (RAG). Those models are typically Transformer models that are…

Ranking is at the core of many artificial intelligence (AI) applications, including search engines, recommender systems, etc. Modern ranking systems are often constructed with learning-to-rank (LTR) models built from user behavior signals.…

Efficiently serving embedding-based recommendation (EMR) models remains a significant challenge due to their increasingly large memory requirements. Today's practice splits the model across many monolithic servers, where a mix of GPUs,…

Product search is one of the most popular methods for customers to discover products online. Most existing studies on product search focus on developing effective retrieval models that rank items by their likelihood to be purchased. They,…

We propose a new application of embedding techniques for problem retrieval in adaptive tutoring. The objective is to retrieve problems whose mathematical concepts are similar. There are two challenges: First, like sentences, problems…